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

Adds substantial behavior beyond the annotations: one read is consumed, a detected change may send email, paused watches are not resumed, and watch-management permission is required. These details clarify side effects, cost, and authorization for a non-read-only operation.

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 short sentences with no wasted wording, and the core action is stated first. The permission and paused-watch exclusions follow naturally.

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?

Covers the important operational context: cost, side effects, permissions, and the paused-watch exclusion. It leaves the return value and watch_id lookup slightly implicit, but no output schema exists and the core invocation requirements are present.

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 has no schema description, and the description only implies it must identify an active watch. It does not explain the integer format or how to obtain the ID, though the parameter name itself is fairly self-explanatory.

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: run a manual check of an active watch. It also distinguishes the action from resuming a paused watch, so an agent can separate it from get_watch, pause_watch, and resume_watch.

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?

Makes the triggering context clear: a requested manual check of an active watch. It includes an explicit exclusion for paused watches, though it does not name specific sibling alternatives such as resume_watch or get_watch.

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