check_watches

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

With no annotations, the description carries the behavioral burden. It discloses that the call returns new matches per watch and, importantly, advances each watch's last-notified marker, which is a side effect. It does not cover error cases or auth, but the core behavior is transparent.

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 with front-loaded purpose, a clear rationale, and the behavioral result. Every sentence earns its place with no redundant filler.

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 one-parameter tool with no output schema, the description covers when to call, what it returns, and what side effect it has. The only noticeable omission is a fuller explanation of the fingerprint value, which is a parameter-level gap rather than a tool-level one.

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 provides only a bare 'fingerprint' string with 0% description coverage. The description adds that the fingerprint is tied to tracking the last check, which gives it semantic meaning, but it never explains what a fingerprint is or how it is obtained, leaving a gap.

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 and resource: pull matches that are new since this fingerprint's last check. This clearly distinguishes it from siblings like search_jobs and watch_intent by focusing on polling watch results rather than searching, reading company info, or authorizing.

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?

Provides explicit usage context: because stdio has no server push, the client should call this at the start of a session. It does not name alternative tools, but the context strongly implies this is the polling complement to watch_intent.

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