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

Annotations already mark it read-only, idempotent, and non-destructive; the description adds useful runtime behavior: cheapest input price first, prices per million tokens, and unpriced models returned as undetermined rather than excluded. This clearly sets expectations for query results.

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 front-loaded with the core purpose and uses four short, information-dense sentences. Each sentence adds a distinct point: selection criteria, ordering, units, missing-price handling, and output nature.

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 an all-optional parameter set and no output schema, the description adequately explains what is returned (satisfying models with corroborating evidence), how results are ordered, and key edge behavior (unpriced models). No critical selection or output caveat appears missing.

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?

With 0% schema description coverage, the description compensates by explaining the main constraint dimensions (context window, capabilities, price ceiling) and the pricing unit. Provider and limit are not explicitly described, but their parameter names are self-explanatory and the overall semantics are clear.

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 states a specific verb ('return') and resource ('models that satisfy it'), and frames the tool as model selection under constraints. It also distinguishes output as candidates with evidence, not a recommendation, which is clear among model-related siblings.

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 specifies when to use it ('Given a need -- minimum context window, required capabilities, a price ceiling') and includes a negative usage cue ('not a recommendation'). It does not explicitly name sibling alternatives or provide an if/then routing rule, so it is strong but not maximally explicit.

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