record_apply

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, it discloses key behavior: the token is single-use and consumed on success or failure, indicating idempotency and ensuring the agent understands the token's lifecycle.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences plus a bullet, no fluff, purpose is front-loaded. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple commit tool with one parameter and an output schema, the description covers the essential behavior and usage. Minor gaps in error details, but overall sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates by explaining the preview_token parameter's origin and single-use nature, adding crucial context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Commit a previously previewed write', using a specific verb ('commit') and resource ('previewed write'), differentiating it from siblings like 'record_write' which handles previews.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly states to use after a preview with record_write, and specifies the token origin. Though it does not explicitly list when not to use, the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.