One read of Claude Developer Platformapi-20261103T223718Z
4 pages moved out of 847 read.
Pages moved
4
significant first
Pages read
847
in this capture
Captured
22:37 UTC
Corpus hash
6cb2b8ca1c92
corpus-hash
What this read moved
1-4 of 4agents-and-tools/tool-use/handle-tool-calls Changed · +41 / -39 lines
from line 57
5757 * `content` (optional): The result of the tool, as a string (for example, `"content": "15 degrees"`), a list of nested content blocks (for example, `"content": [{"type": "text", "text": "15 degrees"}]`), or a list of document blocks (for example, `"content": [{"type": "document", "source": {"type": "text", "media_type": "text/plain", "data": "15 degrees"}}]`). These content blocks can use the `text`, `image`, `document`, or [`search_result`](https://platform.claude.com/docs/en/build-with-claude/search-results) types.
5858 * `is_error` (optional): Set to `true` if the tool execution resulted in an error.
5959
60For example, a successful tool result looks like this:
61
62```json JSON
63{
64 "role": "user",
65 "content": [
66 {
67 "type": "tool_result",
68 "tool_use_id": "toolu_01A09q90qw90lq917835lq9",
69 "content": "15 degrees"
70 }
71 ]
72}
73```
74
6075A `tool_result` that answers a computer use or browser use member block must also echo the same `toolset_name` value as the `tool_use` block; a member result that omits it is rejected. Its `content` is also narrower: a member result may contain only `text` and `image` blocks, and a browser use result may add one [`browser_state`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#track-tabs-and-page-state) block (the [tab-management members](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#tab-management-results) return only that block).
6176
6277<Note>
from line 81
6681 * In the user message containing tool results, the `tool_result` blocks must come FIRST in the content array. Any text must come AFTER all tool results.
6782 * If the assistant turn also called a [server tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools) that has no result block yet, the user message must contain only `tool_result` blocks. Text after the results ends the turn early; for a server tool Claude called directly, the request then fails with a 400 error that names the unresolved server tool. See [Stop reasons and fallback](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons#tool-use).
6883
69 For example, this causes a 400 error:
70
71 ```json
72 {
73 "role": "user",
74 "content": [
75 { "type": "text", "text": "Here are the results:" }, // ❌ Text before tool_result
76 { "type": "tool_result", "tool_use_id": "toolu_01" /* ... */ }
77 ]
78 }
79 ```
80
81 This is correct when the assistant turn calls only client tools:
82
83 ```json
84 {
85 "role": "user",
86 "content": [
87 { "type": "tool_result", "tool_use_id": "toolu_01" /* ... */ },
88 { "type": "text", "text": "What should I do next?" } // ✅ Text after tool_result
89 ]
90 }
91 ```
92
9384 If you receive an error such as “tool\_use ids were found without tool\_result blocks immediately after”, check that your tool results are formatted correctly.
9485</Note>
9586
from line 89
9889</Warning>
9990
10091<AccordionGroup>
101 <Accordion title="Example of successful tool result">
102 ```json JSON
103 {
104 "role": "user",
105 "content": [
106 {
107 "type": "tool_result",
108 "tool_use_id": "toolu_01A09q90qw90lq917835lq9",
109 "content": "15 degrees"
110 }
111 ]
112 }
113 ```
114 </Accordion>
115
11692 <Accordion title="Example of tool result with images">
11793 ```json JSON
11894 {
from line 148
172148 }
173149 ]
174150 }
151 ]
152 }
153 ```
154 </Accordion>
155
156 <Accordion title="Example of text before and after a tool result">
157 For example, this causes a 400 error:
158
159 ```json
160 {
161 "role": "user",
162 "content": [
163 { "type": "text", "text": "Here are the results:" }, // ❌ Text before tool_result
164 { "type": "tool_result", "tool_use_id": "toolu_01" /* ... */ }
165 ]
166 }
167 ```
168
169 This is correct when the assistant turn calls only client tools:
170
171 ```json
172 {
173 "role": "user",
174 "content": [
175 { "type": "tool_result", "tool_use_id": "toolu_01" /* ... */ },
176 { "type": "text", "text": "What should I do next?" } // ✅ Text after tool_result
175177 ]
176178 }
177179 ```
agents-and-tools/tool-use/tool-runner Changed · +4 / -3 lines
from line 25
2525 supportedPlatforms:
2626 Claude API: beta
2727 Claude Platform on AWS: beta
28 Claude Models on Google Cloud (Anthropic managed): beta
2829 Amazon Bedrock: beta
2930 Amazon Bedrock (InvokeModel): beta
3031 Claude Models on Google Cloud (Google managed): beta
from line 1822
18211822
18221823* Availability: Available
18231824
1824| Status | Cloud platforms |
1825| ------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1826| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
1825| Status | Cloud platforms |
1826| ------ | ----------------------- |
1827| Beta | All supported platforms |
18271828
18281829#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
18291830
cli-sdks-libraries/middleware Changed · +4 / -3 lines
from line 24
2424 supportedPlatforms:
2525 Claude API: stable
2626 Claude Platform on AWS: stable
27 Claude Models on Google Cloud (Anthropic managed): stable
2728 Amazon Bedrock: stable
2829 Amazon Bedrock (InvokeModel): stable
2930 Claude Models on Google Cloud (Google managed): stable
from line 220
219220
220221* Availability: Available
221222
222| Status | Cloud platforms |
223| --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
224| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
223| Status | Cloud platforms |
224| --------- | ----------------------- |
225| Available | All supported platforms |
225226
226227#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
227228
build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 Changed · +1 / -1 lines
from line 34
3434
3535* Set `max_tokens` with room for thinking and the reply you expect. Thinking counts toward `max_tokens` even when thinking content isn’t returned to you. A limit sized for a request without thinking can cut the reply off. For agentic coding, set `max_tokens` to 128,000, the model’s maximum, and [stream](https://platform.claude.com/docs/en/build-with-claude/streaming) the response.
3636* Reserve `xhigh` and `max` for work where you’ve measured a quality gain, because thinking and replies get much longer there. At those levels, `between_tools` isn’t accepted, so up-front thinking can’t be turned off.
37* To get less thinking, lower the effort level. From `medium` up, the model thinks briefly before almost every reply, even a greeting, which adds to the time before the first visible token. Asking it in the system prompt to think less doesn’t reliably reduce its thinking. At `low`, it skips thinking on most simple requests.
37* To get less thinking, lower the effort level. Asking the model in the system prompt to think less doesn’t reliably reduce its thinking.
3838
3939Changing the top-level `effort` value between requests invalidates the prompt cache. To change the level partway through a conversation, use a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta) instead, which keeps the cache. A change holds for every later turn until another one replaces it. For example, in an interactive session at `low`, add a change to `high` before the user’s hard problem, and a change back to `low` after Claude answers it. Per-message effort changes need adaptive thinking. With `between_tools`, they return a 400 error, as [Running without up-front thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5#running-without-up-front-thinking) explains.
4040