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

Annotations already cover safety (readOnlyHint, idempotent, non-destructive, closed-world), so the description's job is to add context — and it does: it discloses the returned data surface and pre-empts the main confusion by stating the call does not execute a check. It stops short of saying what happens for an unknown or non-owned watch_id.

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?

Two sentences, zero filler, returned fields front-loaded and the negative constraint placed last where it functions as a boundary. Every clause earns its place.

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 one parameter and no output schema, the description compensates well by naming the response fields. The remaining gap is provenance of the watch_id and error behavior, minor for a read-only single-record fetch.

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 single watch_id parameter carries 0% schema description coverage, and the description only clarifies that it is 'one of the user's watch IDs' — useful ownership scoping but no hint on how the ID is obtained or what an invalid value yields.

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?

States a specific verb+resource ('Read ... watch') and enumerates exactly what comes back: recent check history, last success, retry schedule, delivery state. The closing clause 'Does not run a check' carves it apart from check_watch_now, though it never names that sibling explicitly.

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 'Does not run a check' line implies usage (inspect state rather than trigger execution), but there is no positive guidance such as 'use list_watches first to obtain a watch_id' and no exclusions against pause_watch/resume_watch/delete_watch, which all take the same identifier.

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