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

With no annotations, the description carries the full burden and does so well: it declares public read with no auth, specifies the return payload (rates, provider-checked date, source page, cost breakdown), and documents failure semantics — an unknown model returns UNPRICED, never $0. That is exactly the kind of non-obvious behavior an agent needs before trusting a dollar figure.

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?

The imperative CALL directive is front-loaded and the core mechanics follow in tight sentences. The 'Why it matters' paragraph plus the self-promotional URL are extra weight that does not help an agent invoke the tool, though the cache-heavy-spend point does justify the cache_read_tokens parameter.

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 seven-parameter tool with no annotations and no output schema, the description covers invocation modes, return contents and the unpriced edge case adequately. The remaining gap is the exact semantics of each cache-write/token parameter, which is only partially inferable from the description.

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 only 29%, with five token parameters undocumented in the schema, but the description compensates by naming the rate categories (input, output, 5-minute and 1-hour cache write, cache read, fast-mode) and giving a worked example that shows input_tokens, cache_read_tokens and output_tokens in use. It does not spell out which parameters map to which rate line, so it stops short of fully closing the coverage gap.

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: it returns per-1M-token USD rates for a named model and computes list-price cost from supplied token counts. The scope is unambiguous and no sibling tool (check-package, enrich-ioc, search, etc.) overlaps with it, so an agent can identify it 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?

Explicit trigger: "CALL before quoting what an AI model or an agent session costs, or when a usage report needs dollars," plus the rule that prices come from provider pages rather than memory. It also documents the no-args listing behavior. It does not name a when-not case or an alternative tool, which is the only thing keeping it from a 5.

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