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

Annotations already establish it as a safe, idempotent read (readOnly, idempotent, non-destructive, non-open-world). The description adds genuinely useful context beyond that: the $0.00 free-beta charge, the CC BY 4.0 licensing, and the caveat that a call's cost depends on the model's emitted-token count rather than published list prices.

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 purpose is front-loaded, but the sentence is long and meandering with parenthetical em-dash asides, marketing-inflected claims, and a trailing raw example URL. Only the standard_bench/production_mixed distinction and the 'choose a model before bulk work' instruction clearly earn their place.

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?

An output schema exists, so return-value detail is not needed. The description supplies the dataset distinction, the comparability caveat, and the model-selection intent, making it largely complete for a single-param read tool, though it could more explicitly route against compare_models.

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?

There is a single optional parameter (days) with 100% schema description coverage, so the schema already documents 'Measurement window in days (default 30).' The description adds no format or boundary detail beyond the schema, warranting the baseline 3.

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 names the resource precisely — 'Measured platform cost metadata for one call on each model' — and distinguishes the two datasets (standard_bench vs production_mixed). However, the operative verb is implicit and it doesn't clearly differentiate itself from the sibling compare_models, so an agent must infer the boundary.

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?

It gives explicit context: use standard_bench measurements 'to choose a model before bulk work,' and warns that production_mixed is 'NOT comparable across models.' That is clear when-to-use guidance, though it never names compare_models or list_models as alternatives to route between.

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