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

The description discloses behavior beyond the annotations: a cancelled watch stops re-running immediately and stops counting against the keyless limit. It also surfaces the ownership restriction and the API-key/keyless distinction. This adds useful runtime semantics that readOnlyHint=false alone would not convey.

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?

Three compact sentences earn their place: the main action, the key constraints, and the after-effect. The most important information is front-loaded, and there is no repetition of schema content.

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 two-parameter cancellation tool with a full output schema and clear annotations, the description covers operation, ownership, quota mechanics, and immediate effect. Nothing an agent needs to decide whether and how to call it 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 description coverage is 100%, so the schema already documents watch_id and client_ref thoroughly. The description adds context about ownership and the keyless quota, which indirectly illuminates why client_ref matters, but it does not add specific parameter-level detail 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 opens with 'Stop a standing want by id' — a specific verb and resource that immediately identifies this as the cancellation counterpart to demand.create_watch and demand.list_watches. It also clarifies the ownership constraint ('Only your own can be cancelled'), which distinguishes it clearly from any admin or cross-account operation.

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 description explains when cancellation matters: it is how a keyless caller makes room under the three-watch limit. This gives clear context for choosing cancel_watch when quota is tight or a watch is no longer needed. It does not enumerate alternatives explicitly, but none are needed because cancellation is the obvious inverse of create_watch.

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