watch_resample

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It correctly indicates that the tool triggers a resample (a mutation) and mentions a side effect: 'Emits a Nape honk if drift is detected'. However, it does not disclose other potential side effects, error conditions, or permission requirements. It adds value beyond the name but lacks comprehensive transparency.

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 description is extremely concise: two sentences that front-load the action ('Manually trigger a re-sample'), immediately state the key constraint ('regardless of schedule'), provide usage context, and note a behavioral side effect. Every sentence earns its place with no wasted words.

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?

Given the tool's low complexity (2 parameters, no output schema), the description covers the essential points: what it does, when to use it, and a notable outcome (honk). It does not document return values or error cases, but that is acceptable given the lack of output schema and the tool's straightforward nature. Slightly more detail on preconditions (e.g., that the watch must exist) would push it to a 5.

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 has 2 parameters with 50% description coverage (the 'force' parameter has a description in the schema). The tool description does not explain the 'watch_id' parameter at all, and the 'force' parameter's meaning is already adequately described in the schema. Thus, the description adds no meaningful semantic value beyond what the schema provides, and fails to compensate for the undocumented parameter.

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 tool's purpose: 'Manually trigger a re-sample of a watch' and distinguishes it from automatic scheduled resampling by saying 'regardless of schedule'. It also provides a specific use case: 'on-demand verification after something the scheduler wouldn't know about'. This effectively differentiates it from sibling tools like watch_cancel and watch_status.

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 gives clear guidance on when to use this tool: 'after something the scheduler wouldn't know about (an external change, a suspicion)'. It implies the alternative of waiting for the scheduled resample, but does not explicitly state when not to use it or mention other alternatives. This is above the 'no guidance' level but short of explicit exclusion.

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