check_watch

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses that the tool performs a 'Pure local diff over free search results' and clarifies that it is 'no paid alert service' – a key behavioral trait that prevents misuse. It also explains the different outputs for search vs. listing watches, which is behaviorally nuanced. However, it does not explicitly state whether the operation is read-only (though implied by 'diff') or the return format, leaving minor gaps.

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, no fluff. The primary action and resource are front-loaded, followed by a concise breakdown of watch types and a final clarifying note about the service nature. Every sentence 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?

For a single-parameter tool with no output schema and no annotations, the description is largely complete: it covers purpose, different behavior by watch type, and the mechanism. It does not explicitly state that the watch must already exist via watch_search/watch_listing, but that is implied by 'saved watch.' The return format is not described, but given the simplicity, this is not a critical omission.

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 input schema already describes the only parameter ('Watch name to check') with 100% coverage, so the baseline is 3. The description adds value by explaining how the watch's type (search/listing) affects the result, but this is contextual to the tool, not the parameter syntax. No additional parameter semantics are needed beyond the schema.

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 clearly states the action ('Re-run a saved watch') and the resource ('watch'), then specifies exactly what it reports for each watch type (NEW listings for search watches, PRICE DROP for listing watches). This distinguishes it from siblings like list_watches (which probably just lists watches) and watch_search/watch_listing (which create watches). The tool's purpose is unambiguous and context-specific.

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 implies when to use it (when you have a saved watch and want changes) without explicitly naming alternative tools. It contrasts with create/remove watch tools by focusing on the 're-run' aspect, but doesn't explicitly say 'use this instead of list_watches when you want a specific watch's diff.' The context is strong enough for inference, but an explicit 'when to use' statement would make it a 5.

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