model_performance

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

No annotations provided, so description carries full burden. It mentions 'background-updated' indicating data is not real-time, which is a key behavioral trait. However, it omits details about data freshness, update frequency, permission requirements, or any side effects. More behavioral context needed for safe usage.

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?

Description is concise, starting with the main purpose in one sentence, then listing parameters in a clear Args format. No superfluous text. Well-structured for quick scanning.

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?

With 3 optional parameters, output schema present, and no annotations, the description covers the essential behavior (3-day window, background update, parameter purposes). However, it does not mention default values or clarify whether the aggregation is per model or per endpoint (though 'per model' is stated). Adequate but leaves some gaps.

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?

Despite 0% schema description coverage, the description explains all three parameters (endpoint, sort_by, limit) with meanings and valid values. For sort_by, it lists the possible field names. This adds meaningful context beyond the schema's type information. Default values are only in schema, not description, but the explanation is sufficient.

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?

Description clearly states it returns aggregated call metrics per model for the last 3 days, with a note about background-updated data. It distinguishes from sibling list_models (list models) and invoke_model (invoke model). The Chinese phrase '近3天' may cause slight ambiguity but overall purpose is clear.

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?

No guidance on when to use this tool versus alternatives like list_models or invoke_model. No explicit when-to-use or when-not-to-use criteria. The description only covers parameters, not usage context.

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