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

Annotations declare destructive and idempotent, and the description adds genuine context beyond them: it spells out what 'permanent' means, that a repeat call answers with the same stopped_at instead of an error, and it enumerates specific error codes with recovery actions. This is exactly the extra behavioral detail annotations cannot carry.

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-loaded with the core semantics ('for good: instant, permanent and idempotent') before edge-case handling; the example call and guide link are purposeful rather than filler. The error-recovery sentence is dense but every clause maps to a real decision the caller must make.

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 still discloses the return signal (stopped_at) and the error taxonomy, and points to get_tool_guide / the tools.json fragment for the full contract. Nothing an agent needs to invoke this destructive, idempotent operation correctly is missing.

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 coverage is 100% and both parameters are documented in the schema, including the shopping_session_id's non-authority note, so the description only reinforces via the example call. Baseline 3 when the schema does the heavy lifting.

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?

"Stops a back-in-stock watch for good: instant, permanent and idempotent" gives a specific verb, resource and effect, and the resource ('back-in-stock watch') distinguishes it from the sibling stop_recall_watch without opening either 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?

Explicitly states the trigger condition ("Use when the person no longer wants the watch") and routes failure paths (retry once, then submit_feedback; watch_not_found = nothing to do). It does not name a sibling alternative such as stop_recall_watch, but the guidance for when and what happens next is clear and actionable.

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