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

With readOnlyHint=true the safety profile is already covered, and the description adds genuine behavioral context: credits are never converted to money (a real interpretation constraint) and colliding dimension labels carry qualifiers, e.g. 'Web search (context size: high)'. It stops short of noting rate limits or the exact output structure, but it meaningfully exceeds the annotation.

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 tight sentences, front-loaded with what the tool returns before moving to the two output caveats. Every sentence carries content; the label-collision example is slightly niche but directly aids result interpretation.

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?

There is no output schema, so the description must convey the return shape; it communicates the comparative format, the credit caveat, and label disambiguation, which is helpful. It still leaves the actual compared dimensions and result structure vague, which is a notable gap for a comparison tool with no output schema.

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?

The description says nothing about the single `models` parameter, and per the context signal schema description coverage is 0%, so the description fails to compensate for the documented gap. It does not mention the 2-8 item bounds or the `provider/slug` format that the agent must supply.

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: 'Returns the current prices of several models side by side.' This clearly separates it from single-model retrieval siblings like get_model_price, though it never names those siblings explicitly. An agent can grasp the comparison scope immediately.

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 word 'several' and the side-by-side framing, and the credit-vs-token caveat hints at when results are meaningful. However, no alternative tool is named and there is no explicit when-not guidance, so the agent must infer this is the multi-model counterpart to get_model_price.

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