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

Annotations already cover readOnly, idempotent, and non-destructive behavior. The description adds a paid cost (0.10 USDC per call) and that the result is sorted tightest first, which are useful. However, it omits details like pagination or whether many rows are returned, which could matter for an agent. Since annotations handle safety, a 3 is appropriate.

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 one concise sentence, front-loading the paid cost and then stating the core function. It is efficient and easy to scan. It could be slightly more structured (e.g., noting the sort order more explicitly), but overall it is well-sized with no filler.

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 simple read-only tool with one optional parameter, the description is adequate but not complete. It states the output (scores for all models, sorted) but does not describe return structure, limits, or if there are any special cases (e.g., missing data for a day). Without an output schema, an agent might need to infer the exact fields, so a 3 is fair.

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 'day' is fully described in the schema with format and default. The tool description does not add extra meaning about the parameter—it only implies a single day via 'for one day'. With 100% schema coverage, the baseline of 3 holds; the description contributes nothing 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 states a clear function: returns capacity stress scores for all GPU models for one day, sorted tightest first. It is specific about the resource (GPU model capacity stress) and the time scope. However, it does not explicitly differentiate itself from sibling tools like capacity_stress or capacity_headline beyond the 'board' phrasing, so it earns a 4 rather than a 5.

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?

There is no guidance on when to use this tool versus alternatives. The description only explains what it does; it does not mention scenarios like comparing across days (use capacity_history) or getting a headline number (capacity_headline). Without such exclusions or context, an agent may not know when this is the best choice.

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