Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsModel Context Protocol 28 Jul 2026
One change · mcp

Client Best Practices changeddocs/2025-03-26/develop/clients/client-best-practices

Upstream edited this page at 28 Jul 2026 15:42 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 20 Oct 2026 20:07 UTC.

Upstream edited
Recorded here
Lines+2added
Lines−2removed
From line 10 where the diff opens
First seen 26 Aug 2026 this site's first read of the page
Recorded edits3to this page, all time

The whole hunk

from line 10, old and new numbered
/
lines
from line 10
1010 
1111Naive MCP host implementations pass the tool definitions of every connected server directly to the model at the start of each conversation. For a handful of tools, this is perfectly reasonable. But when a host has access to dozens of servers exposing hundreds of tools, those definitions alone can consume the majority of the context window before the model has even read the user's message.
1212 
13<img src="https://mintcdn.com/mcp/JXfd5cBmEUh_qPUI/images/progressive-discovery.svg?fit=max&auto=format&n=JXfd5cBmEUh_qPUI&q=85&s=db39f47006107f04af43b5eeae2d6022" alt="Comparison of loading all tools upfront versus discovering tools on demand. The upfront approach consumes ~150,000 tokens on definitions alone, while progressive discovery uses ~2,000 tokens by loading only what the task requires." width="760" height="440" data-path="images/progressive-discovery.svg" />
13![Comparison of loading all tools upfront versus discovering tools on demand. The upfront approach consumes \~150,000 tokens on definitions alone, while progressive discovery uses \~2,000 tokens by loading only what the task requires.](https://mintcdn.com/mcp/JXfd5cBmEUh_qPUI/images/progressive-discovery.svg?fit=max\&auto=format\&n=JXfd5cBmEUh_qPUI\&q=85\&s=db39f47006107f04af43b5eeae2d6022)
1414 
1515Progressive discovery avoids this:
1616 
from line 156
156156Programmatic tool calling is powerful and allows for more efficient use of MCP tools and resources, but requires
157157clients to implement a sandbox environment.
158158 
159<img src="https://mintcdn.com/mcp/JXfd5cBmEUh_qPUI/images/programmatic-tool-calling.svg?fit=max&auto=format&n=JXfd5cBmEUh_qPUI&q=85&s=a2be82d097bb7cd7c7fd415918b1571d" alt="Comparison of direct tool calling versus programmatic tool calling. Direct calling passes every intermediate result through the model (~100K+ tokens). Programmatic calling sends a ~200-token script to a sandbox, which executes the tool calls and returns a ~15-token summary." width="900" height="900" data-path="images/programmatic-tool-calling.svg" />
159![Comparison of direct tool calling versus programmatic tool calling. Direct calling passes every intermediate result through the model (\~100K+ tokens). Programmatic calling sends a \~200-token script to a sandbox, which executes the tool calls and returns a \~15-token summary.](https://mintcdn.com/mcp/JXfd5cBmEUh_qPUI/images/programmatic-tool-calling.svg?fit=max\&auto=format\&n=JXfd5cBmEUh_qPUI\&q=85\&s=a2be82d097bb7cd7c7fd415918b1571d)
160160 
161161### How It Works
162162 
Feedback