gpu_watch

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's safe. The description adds information about returning multiple frames and aggregated statistics, and mentions defaults. No contradictions. It does not detail concurrency or cancellation, but annotations cover the safety profile.

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: first explains functionality, second provides a use case and defaults. No fluff, every sentence adds value. Efficient and front-loaded.

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 no output schema, the description adequately describes the output (raw frames and per-card statistics). Parameters are fully covered. The tool's niche is clear compared to sibling tools. It could optionally describe the structure of the return value, but it is complete enough for an agent.

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?

Schema coverage is 100%, so parameters are fully described in the schema. The description adds default values and range context (5 samples, 1000ms, 2-60, 100-10000), but this is already in the schema descriptions. Baseline 3 is appropriate since the schema does the heavy lifting.

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 ('take N snapshots'), the resource ('gpu_status'), and the result ('raw frames and per-card min/max/avg statistics'). It distinguishes from siblings like 'gpu_status' which likely returns a single snapshot. This is a specific verb+resource combination with sibling differentiation.

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 provides a clear use case: 'is this training run stable?'. It implies usage for monitoring stability over time. While it doesn't explicitly state when not to use or list alternatives, the context is clear enough for an agent to decide.

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