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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior: deduplication per model, ranking by each model's own lowest current price, and descending order — details an agent could not infer from the name.

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?

A single front-loaded sentence that gives the result shape, the counting rule, and the ordering with no filler. Nothing could be removed without losing information.

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?

For a read-only ranking tool with full schema coverage and no output schema, the description covers purpose, counting semantics, and ordering adequately. It leaves return-value structure and tie-breaking unstated, which is acceptable given the simplicity but not exhaustive.

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 all four parameters are already documented, which sets the baseline at 3. The description adds no parameter detail of its own; 'Same arguments as cheapest_models' offloads semantics to another tool rather than adding meaning here.

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?

States a specific verb+resource+ordering: 'the n most expensive MODELS for a job (task)', 'highest first'. It also pins down the counting rule (each model once, at its own lowest current price), so an agent can tell it apart from cheapest_models and median_models without opening either schema.

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 phrase 'the top of the market' plus the contrast baked into the name against cheapest_models/median_models makes the use case clear, and 'Same arguments as cheapest_models' points to a comparable tool. It stops short of an explicit when-not or an outright named alternative, so it's a clear context rather than a routing rule.

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