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

Goes well beyond the annotations: it specifies what is actually destroyed (the stored callback URL or email), that the covered checkout can never be watched again, and that the operation is irreversible. It also documents the error taxonomy and retry/escalation path, which annotations cannot express.

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?

Front-loads the core action and consequences, then error recovery, then references, then an example — a sensible ordering. Slightly dense with a trailing 'Nothing follows.' and guide pointers, but nearly every sentence carries 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?

With no output schema, the description covers the terminal outcome ('Nothing follows'), irreversibility, idempotency, and failure handling, which is everything an agent needs to invoke this destructive tool correctly.

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 100%, so both parameters are already documented, and the description's example call only restates the required watch_token shape. It adds no semantic detail on watch_token format or on the optional shopping_session_id beyond what the schema provides, matching the baseline 3.

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?

Names a specific verb (stops) and resource (recall watch) and immediately scopes the effect: 'instant, permanent and idempotent,' erasing the stored callback URL or email. This is distinguishable from its close siblings get_recall_watch and stop_back_in_stock_watch without opening any schema.

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?

Gives an explicit trigger ('Use when the person asks to stop the watch') plus concrete error-recovery branches: watch_not_found means do nothing further, watch_failed means retry once then call submit_feedback. It lacks an explicit 'when not to use' or a named alternative (e.g., stop_back_in_stock_watch for a different watch type), so it falls just short of 5.

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