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

With no annotations, the description carries the burden. It usefully discloses that matching goes through the index's name normaliser and that multiple basket entries may be returned, but it says nothing about result ordering, ambiguity handling, or behavior when no match exists.

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 opens with what is returned and its units, then spends the remainder on input handling. Every clause carries information; no 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 one-parameter read lookup with no output schema, the description covers input forms, matching mechanics, and the multi-match return shape. Slightly more on ambiguity or missing-model behavior would close the loop.

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 0%, so the description must compensate, and it does: the single `name` parameter accepts 'any common name' with three concrete format examples and explains that resolution is fuzzy via a name normaliser. Only the failure/ambiguity semantics remain unstated.

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 concrete resource and unit: blended list price per 1M tokens for a single model, resolved by name. It's clear this is a price lookup, though it doesn't name a sibling (e.g. cost_per_task or basket) to sharpen the boundary.

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 examples imply accepted input formats, which gently tells the agent how to call it, but there is no explicit when-to-use-this-instead-of guidance versus cost_per_task, basket, or index_latest. Usage is inferred rather than stated.

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