changedetection_delete_watch

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

Annotations already declare destructiveHint and idempotentHint, so the bar is lower, but the description still adds the key consequence — the watch's entire history is destroyed — and the dry-run-by-default safety pattern. Missing only permission or irreversible-forever caveats.

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 terse fragments — action, endpoint, dry-run caveat — with the destructive consequence front-loaded and zero padding.

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 2-parameter destructive tool with full annotations and no output schema, the description covers what is destroyed and how to preview. Only the absence of post-deletion return information and sibling routing keeps it from a 5.

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%, with both uuid and confirm fully documented including the rejected false/string-true cases. The description restates the dry-run behavior already in the schema and adds no new parameter semantics, so baseline 3 applies.

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 and resource plus its blast radius ('delete a watch and all of its history'), which meaningfully separates it from changedetection_delete_history, which the description does not explicitly name. An agent can classify it as a destructive watch-level operation without opening the 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?

Conveys how to preview safely ('Omit confirm for a dry-run'), but gives no guidance on when to prefer this over changedetection_delete_history, changedetection_set_watch_state, or how to recover the UUID. Usage is implied rather than routed.

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