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

Beyond the readOnlyHint annotation, the description discloses the aggregation rule (one row per model), the pricing basis (each model's own lowest current price, input tokens by default), and the shape of each returned row (price, where it is, card_url). That is useful behavioral context an agent could not get from the annotations. It does not cover how many rows may be returned or ordering guarantees when ties occur.

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?

Two compact sentences with the aggregation and default price basis front-loaded ahead of the row-shape detail; nothing is padded. The final clause 'where it is and card_url' is grammatically loose and slightly opaque, which costs a point.

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 four parameters, no output schema, and a read-only profile, the description supplies the essentials: what the result set is, how models are deduplicated, the default price basis, and the fields of each row. It is close to complete for this complexity, missing only ordering and result-set size cues.

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?

Schema description coverage is 100%, so the enum values, defaults, and the n cap are already documented in the schema itself. The description only reinforces the default pricing component ('input tokens by default') and the notion of task-as-job, adding marginal meaning beyond the structured fields. Baseline 3 applies.

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 uses a specific verb and resource: it returns the n cheapest models for a given task, with the key semantic that each model appears once at its own lowest current price. That dedupe-per-model framing is meaningfully different from an offer-level tool, though it never names a sibling tool so the contrast is implicit rather than stated.

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?

Usage is implied by the model-level aggregation ('each model counted once at its own lowest current price'), which suggests this is the pick-a-model tool rather than the pick-an-offer tool. However, there is no explicit guidance on when to choose this over cheapest_offers, cheapest_for_workload, or compare_models, and no exclusions are stated.

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