llm_model_usage

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

No annotations are provided, so the description carries full burden. It correctly indicates a read-only analysis tool with a time window. However, it does not disclose potential performance impact, rate limits, or data freshness beyond the look-back period.

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 concise and well-structured: a one-line purpose, a bullet list of statistics, and a brief Args/Returns section. Every sentence adds value, though slightly redundant phrasing ('Model usage statistics') could be trimmed.

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 simplicity (one optional parameter, output schema exists), the description adequately covers functionality. It explains what statistics are shown and the time window, meeting completeness requirements without unnecessary detail.

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 0% description coverage, but the description's Args section explains the 'hours' parameter's meaning and default. This adds value beyond the schema, even though the schema is minimal.

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: 'Analyze which models are being selected in routing.' It lists specific statistics (top models, task types, classification methods, success rates), distinguishing it from sibling tools like llm_usage which likely tracks overall usage.

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 explains the tool's functionality and the hours parameter, but does not provide guidance on when to use this tool versus alternatives (e.g., llm_check_usage, llm_track_usage). No exclusions or when-not-to-use advice is given.

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