watch_health

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

No annotations are provided, so the description bears full burden. It discloses the sampling duration (up to 60 seconds) and the reported metrics, but does not clarify if the tool is read-only or has side effects (e.g., resetting counters). No contradictions.

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 a single sentence that efficiently states the action, scope, and output metrics. It is front-loaded and contains no redundant information.

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 simplicity of the tool (one parameter, no output schema), the description covers the main behavioral aspects: sampling duration and specific metrics. However, it could be slightly more precise about the return format (e.g., single object vs. array).

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 only parameter (seconds) has no description in the tool description; schema coverage is 0%. While the name and default (10) are somewhat self-explanatory, the description adds no extra meaning or usage details 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 ('sample OBS stats') and the result ('report a stream-health verdict') with specific metrics (dropped-frame %, GPU misses, CPU pressure). It distinguishes from siblings like get_stats (raw stats) and health_check (likely simple check) by emphasizing the sampling over time.

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 the tool is for monitoring stream health over a period, but it does not explicitly state when to use it compared to alternatives like health_check or get_stats. No guidance on when not to use it or prerequisites.

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