fitbit_cancel_draft

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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false and a closed (non-open-world) scope. The description usefully clarifies the *extent* of that destruction — it only discards a local draft and never touches Google-side records — which is real context beyond the flags. It stops short of covering failure modes (e.g. canceling an already-committed preview) or required auth.

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?

One compact sentence with the action front-loaded and the critical non-effect ('does not delete Google records') trailing it. Nothing is wasted and no filler precedes the useful information.

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 low-complexity, single-parameter mutation with annotations covering the safety profile and no output schema, the description covers purpose and blast radius adequately. It is still incomplete on the two things an agent most needs: where operationId comes from and what state the draft is left in after cancellation.

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?

Schema description coverage is 0% and the description never mentions the single required parameter. An agent gets no hint that operationId is the handle produced by a prior preview call, nor what an invalid/stale id means — the only guidance is the JSON-schema UUID pattern, which is necessary but not sufficient for correct invocation.

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?

States a specific verb and object ('Cancel an untouched local preview') and immediately bounds the effect ('does not delete Google records'), which implicitly separates it from the delete-oriented sibling fitbit_remove. It does not name a sibling outright, but the scope is unambiguous.

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?

The qualifier 'untouched' implies when this tool applies (a preview that has not been committed or modified) and the negation implies when it does not (when you actually want to remove Google records). However, no alternative tool is named and no prerequisite such as 'use the operationId returned by fitbit_preview_meal/preview_water' is given, so routing is left to inference.

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