888 pages for tools.

Query compliance activities Claude Developer Platform · in the page api/compliance/activities/list …_always_allow_disabled"` The "Always allow" option for connector tools in Cowork was disabled for the organization, so each use of a connector tool that can make changes requires approval. Read-o… Apps Claude Developer Platform · in the page api/compliance/apps …esence-only marker message is emitted when it was set. The request's `tools[]` definitions are never included as transcript messages. Project-level instructions (such as CLAUDE.md files) appear in the… Sessions Claude Developer Platform · in the page api/compliance/apps/sessions …esence-only marker message is emitted when it was set. The request's `tools[]` definitions are never included as transcript messages. Project-level instructions (such as CLAUDE.md files) appear in the… Local Claude Developer Platform · in the page api/compliance/apps/sessions/local …esence-only marker message is emitted when it was set. The request's `tools[]` definitions are never included as transcript messages. Project-level instructions (such as CLAUDE.md files) appear in the… Messages Claude Developer Platform · in the page api/compliance/apps/sessions/local/messages …esence-only marker message is emitted when it was set. The request's `tools[]` definitions are never included as transcript messages. Project-level instructions (such as CLAUDE.md files) appear in the… Retrieve local session messages Claude Developer Platform · in the page api/compliance/apps/sessions/local/messages/list …esence-only marker message is emitted when it was set. The request's `tools[]` definitions are never included as transcript messages. Project-level instructions (such as CLAUDE.md files) appear in the… Organizations Claude Developer Platform · in the page api/compliance/organizations …- `"code_execution_network_egress_enabled"` - `"connector_tools_default_always_allow"` - `"content_redaction_enabled"` - `"cowork_trusted_devices_required"` - `"deskto… Settings Claude Developer Platform · in the page api/compliance/organizations/settings …- `"code_execution_network_egress_enabled"` - `"connector_tools_default_always_allow"` - `"content_redaction_enabled"` - `"cowork_trusted_devices_required"` - `"deskto… Get effective organization settings Claude Developer Platform · in the page api/compliance/organizations/settings/retrieve …- `"code_execution_network_egress_enabled"` - `"connector_tools_default_always_allow"` - `"content_redaction_enabled"` - `"cowork_trusted_devices_required"` - `"deskto… errors Claude Developer Platform · in the page api/errors …thinking can't be set to `disabled`. Use `thinking: {"type": "between_tools"}` for the lowest thinking setting, which turns off up-front thinking. Sending `thinking: {"type": "disabled"}` returns a 40… Messages Claude Developer Platform · in the page api/messages …string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to.… Batches Claude Developer Platform · in the page api/messages/batches …pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to.… Create a Message Batch Claude Developer Platform · in the page api/messages/batches/create …pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to.… Retrieve Message Batch results Claude Developer Platform · in the page api/messages/batches/results …ed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](… Count tokens in a Message Claude Developer Platform · in the page api/messages/count_tokens …API can be used to count the number of tokens in a Message, including tools, images, and documents, without creating it. Learn more about token counting in our [user guide](https://platform.claude.co… Create a Message Claude Developer Platform · in the page api/messages/create …string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to.… Models Claude Developer Platform · in the page api/models …09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp… List Models Claude Developer Platform · in the page api/models/list …09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp… Get a Model Claude Developer Platform · in the page api/models/retrieve …09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp… Message Batches API Claude Developer Platform · in the page build-with-claude/batch-processing …n a batch. This includes: * Vision * Tool use, including all [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools) (web search, web fetch, code execution, MCP con… cache-diagnostics Claude Developer Platform · in the page build-with-claude/cache-diagnostics …and tells you where they diverged (the model, the system prompt, the tools, or the message history) so you can fix the root cause instead of guessing. ## How cache diagnostics works For each reques… claude-in-amazon-bedrock Claude Developer Platform · in the page build-with-claude/claude-in-amazon-bedrock …a newer Claude model](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model). </Tip> ## Feature support For the full feature list with… claude-in-microsoft-foundry Claude Developer Platform · in the page build-with-claude/claude-in-microsoft-foundry …tead) * [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool… claude-on-amazon-bedrock-legacy Claude Developer Platform · in the page build-with-claude/claude-on-amazon-bedrock-legacy …thinking) * [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Com… claude-on-vertex-ai Claude Developer Platform · in the page build-with-claude/claude-on-vertex-ai …a newer Claude model](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model). </Tip> ### Making requests Before running requests you m… claude-platform-on-aws Claude Developer Platform · in the page build-with-claude/claude-platform-on-aws …a newer Claude model](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model). </Tip> ## Making requests Claude Platform on AWS uses th… sent_count = len(messages sent in the compaction request) Claude Developer Platform · in the page build-with-claude/compaction …e in that case. </Note> ## Combining with other features ### Server tools When using server tools (such as web search), the compaction trigger is checked at the start of each sampling iteration. Co… compaction-on-demand Claude Developer Platform · in the page build-with-claude/compaction-on-demand …with `stop_reason` `"compaction"`. Send the same `system` prompt and `tools` that you use for the rest of the conversation. The summarizer reads them, and if you keep turns after the block on a model… compaction-thinking-blocks Claude Developer Platform · in the page build-with-claude/compaction-thinking-blocks …ept turns then start with Claude's reply to it. * **`system` and the `tools` not marked `defer_loading: true` don't change.** They are the same on the compaction request as on the requests that produc… compaction-threshold Claude Developer Platform · in the page build-with-claude/compaction-threshold …e in that case. </Note> ## Combining with other features ### Server tools When using server tools (such as web search), the compaction trigger is checked at the start of each sampling iteration. Co… context-editing Claude Developer Platform · in the page build-with-claude/context-editing …using [`tool_runner`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner). Generates a summary and replaces full conversation history. See [Client-side compaction](https://plat… context-windows Claude Developer Platform · in the page build-with-claude/context-windows …ocks](https://platform.claude.com/docs/images/context-window-thinking-tools.svg) <Steps> <Step title="First turn architecture"> * **Input components:** Tools configuration and user message… effort Claude Developer Platform · in the page build-with-claude/effort …se. To turn off up-front thinking, send `thinking: {"type": "between_tools"}` instead of `"disabled"`. It's the lowest thinking setting on Claude Sonnet 5.5, and it works at `low`, `medium`, and `hig… extended-thinking Claude Developer Platform · in the page build-with-claude/extended-thinking …explain this exception. * Interleaved thinking is only supported for [tools used through the Messages API](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). How platforms treat… fallback-credit Claude Developer Platform · in the page build-with-claude/fallback-credit …. </Step> </Steps> <Note> If the refused request executed server tools, a tokenless retry re-runs and re-bills those tools. In that case, surface the 400 error to your caller instead of falling t… files Claude Developer Platform · in the page build-with-claude/files …[code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) to provide inputs (for example, datasets and documents) and then download outputs (for example… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …ax-tokens 1024 --format jsonl <<'YAML' model: claude-opus-5-5 tools: - name: get_weather description: Get the current weather in a given location input_schema:… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …system, output_config={"effort": EFFORT}, tools=[BASH_TOOL, REPORT_TOOL], messages=messages, timeout=REQUEST_TIMEOUT_SECONDS, ) as str… mid-conversation-system-messages Claude Developer Platform · in the page build-with-claude/mid-conversation-system-messages …) are in beta on the same models. On the Claude API, send the `inline-tools-2026-09-15` beta header, which also covers [defining a tool inside a `tool_addition` block](https://platform.claude.com/docs… overview Claude Developer Platform · in the page build-with-claude/overview …capabilities:** Control how Claude reasons and formats responses. * **Tools:** Let Claude take actions on the web or in your environment. * **Tool infrastructure:** Handles discovery and orchestration… pdf-support Claude Developer Platform · in the page build-with-claude/pdf-support …sing. * [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview): To extract specific information from documents for use as tool inputs. </Step> </Steps> ### Estimate… preserved-thinking Claude Developer Platform · in the page build-with-claude/preserved-thinking …ore the thinking block has changed.** The top-level `system` prompt, `tools`, and `messages` before the block are its prefix. If the prefix differs from what you sent when the block was produced, that… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …es the full prefix** Prompt caching references the entire prompt: `tools`, `system`, and `messages` (in that order), up to and including the block designated with `cache_control`. </Tip> *** ## P… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …isabled, user-facing progress updates, safeguard false positives, and tools for complex visual inputs.… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …this level are also a good prompt to re-evaluate which instructions, tools, and guardrails are still needed. The patterns below cover the behaviors that most often require tuning. <Note> For API p… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …Answers about charts and dense images miss detail: [Give vision work tools to crop and zoom](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1#give-v… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …explicitly instruct the model about when and how to properly use its tools. For instance, if you find that the model is not using your web search tools, clearly describe why and how it should. ## Us… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …longer be needed. Vision performance is strongest when the model has tools to iteratively analyze, crop, and visually verify its work, and tool use is a more cost-effective lever than thinking alone.… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …* Answers about dense charts, diagrams, or screenshots miss detail: [Tools for complex visual inputs](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …is more agentic than Claude Sonnet 4.6 by default and will reach for tools and run self-verification loops more readily. With thinking disabled, the model is less likely to reach for tools or conside…