Check watches

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

The annotations (readOnlyHint=false, idempotentHint=false) are consistent with the description's disclosure that the call advances each watch's last-notified marker, and the description goes well beyond them: first-pull semantics, per-result is_first_pull, 100-result truncation, board_error handling, and the fact that closed postings aren't re-reported. That is unusually rich side-effect and return-shape disclosure.

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 purpose and trigger are front-loaded in the first two lines, and the remaining sentences convey distinct behaviors rather than padding. It is on the long side, but nearly every sentence carries operational information the agent would otherwise get wrong.

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 and a single undocumented parameter, the description compensates by naming the returned fields (new_matches, closed_since_last, total_matching, board_error, is_first_pull, truncated) and warning how to present a first pull and a truncated result. Nothing essential for correct invocation or reporting 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 0%, so the schema documents nothing about 'fingerprint'. The description adds meaning by framing it as the key to 'this fingerprint's last check' (i.e., per-client watch state), but it never states the fingerprint's format or where the agent obtains it.

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 a precise verb+resource+scope: 'Pull matches that are new since this fingerprint's last check,' and explains the pull-vs-push model that motivates the tool. It does not explicitly name or exclude the closest siblings (search_jobs, read_board), so an agent must infer the boundary itself.

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?

It gives a concrete usage trigger — 'call this at the start of a session' — which is exactly the context an agent needs. It stops short of naming alternatives or stating when not to call it (e.g., versus search_jobs for ad-hoc queries).

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