Sweep 19 Sep 2026 · 02:36Z Build v2.1.278 500 read Stable v2.1.267 Latest v2.1.278 Next v2.1.278 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.273 ·

New guidance for learning connector-tool schemas before publishing an Artifact or Doc

Claude now has explicit guidance on how to safely learn a connector tool's argument and result shapes before publishing a page that uses it

TierUnder the hoodhow much it should matter to you
Useful1my rating, 1 to 5
Signal1worth watching, 1 to 5
AreaArtifactswhat it touches
KindInternal Changesin v2.1.273,
Group of 2 Under the hood

Claude now has explicit guidance on how to safely learn a connector tool's argument and result shapes before publishing a page that uses it

What

A new block of guidance text instructs Claude on how to handle connector (MCP) tools when publishing something like a Claude Doc or Artifact page:

  • Take argument names for a loaded connector tool from the tool's own input schema, not from guesswork.
  • Only learn a tool's result shape by making a safe, real call to it, never by inferring it from a write call.
  • Use describeTool(server, tool) when the published page needs to read a tool's schema at view time, since the authoring session cannot see that information before publishing.
  • Disclose to the user, rather than embedding in the page itself, whenever a tool's shape had to be guessed.

Why

This reduces the chance of a published page calling a connector tool with wrong argument names or misinterpreting its results, since the model is directed to verify tool shapes safely instead of guessing.

See this entry in the whole of v2.1.273 →