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

Annotations already declare readOnly, idempotent, and closed-world behavior, so safety is covered. The description adds genuine behavioral value by disclosing the selection rule (≤5 performance-index points lower for the same usage), which tells the agent how candidates are chosen rather than just that a lookup occurs.

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 with no filler. The constraint that defines the tool is stated immediately and nothing is repeated from the title or schema.

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?

The core selection semantics are explained, but for a 3-parameter tool with no output schema the description leaves the undocumented parameters and the shape of the result (e.g., a single model vs. a ranked list, and whether cost savings are returned) unstated.

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 0%, so the description must compensate for all three parameters, and it largely does not. "For the same usage" hints that token usage matters but never explains that model is the input model or that input_tokens/output_tokens default to 1,000,000 and 250,000.

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 (finds) and resource (a cheaper model) with a precise selection constraint (at most five performance-index points lower). This is clearly distinct in intent from siblings like find_models or get_model, though it does not name or explicitly contrast any sibling.

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?

"For a model you use today" implies the usage context (cost-reduction for an existing model), which is reasonable implied guidance. However, it never states when not to use it or names an alternative such as recommend_models or best_for_task, leaving routing to inference.

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