list_watch_changes

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It explicitly states the endpoint is read-only, has no server-side 'last checked' state, does not interfere with deliveries, and explains paging semantics (meta.cursor, meta.hasMore) and changeKind meanings. This is exemplary transparency beyond what annotations would have supplied.

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?

The description is well-structured with bold topic labels (scoping, safety, paging, changeKind, cost). Each paragraph earns its place by addressing a distinct aspect. It is front-loaded with the core purpose and remains concise despite covering multiple behavioral details.

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?

There is no output schema, so the description compensates by explaining return semantics: it lists per-item changes, mentions null citation/title for certain corpora, and describes meta.cursor/meta.hasMore behavior. Combined with the schema's parameter descriptions, this is complete enough for an agent to correctly invoke and interpret results.

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?

The schema already covers 83% of parameters with detailed descriptions. The tool description adds interaction-level semantics: how sinceId and meta.cursor combine for paging, why order=asc is best for catch-up, and the meaning of changeKind values. It does not add much about watch_id but is not needed since the watch scoping is clear from the description.

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 opening sentence explicitly defines the tool as listing sections a watch's source added, amended, or removed, newest first. It also distinguishes the tool from mere notification counts ('not "3 sections changed" but which three'), making the purpose clear and differentiating it from sibling tools like get_watch_change_diff and list_watch_deliveries.

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 provides clear usage context: it is scoped to the watch's own lifetime, safe to poll alongside webhook/email watches, and includes paging guidance (using sinceId with meta.cursor, order=asc while catching up). It does not explicitly name alternative tools for when-not-to-use, but the 'per-item detail behind counts' phrasing positions it against count-level notifications.

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