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

No annotations, so the description carries the full burden. It does add real context beyond the schema: the operation is free, and data is 'Provider-declared (models.dev)', warning the agent that values are third-party sourced rather than authoritative. It omits auth requirements, rate limits, and missing-key behavior for a lookup tool.

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?

Three short sentences, front-loaded with the outcome, then the payload, then the routing hint. Every clause informs a decision; nothing is filler.

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 single-parameter read with no output schema and no annotations, the description conveniently enumerates the returned fields, which covers most of what an agent needs. Only minor gaps remain: error behavior for unknown keys and whether the data is cached or live.

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 coverage is 100% and the single 'key' parameter already has the 'provider/model, e.g. openai/gpt-4o' description. The description's inline example (anthropic/claude-sonnet-4) repeats that, adding no new semantics such as normalization or case sensitivity. 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?

States a specific verb and resource (full card for a single model/provider key), lists exactly what the record contains (price per 1M tokens, context, capabilities), and gives a concrete key example so the agent knows the shape of the input. It is clearly distinguishable from find_model, the search 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?

Explicitly routes the agent: 'Use find_model to search' implies this tool is for fetching one already-known key. It also flags 'Free.' as a cost condition. It does not state what happens on a nonexistent key, so there's no failure-mode guidance.

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