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

Annotations only declare readOnlyHint and openWorldHint; the description adds the critical non-obvious behavior that this is a paid tool ($0.02 USDC via x402) whose call returns payment requirements rather than data, requiring a second paid step. That two-phase payment flow and the cost are exactly the kind of behavioral detail an agent cannot infer from structured fields.

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 paid cost and data scope are front-loaded, followed by filters and the payment mechanism. It is a single dense paragraph that is slightly run-on, but nearly every clause carries information an agent needs.

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?

With no output schema and thin annotations, the description does the heavy lifting: it discloses the payment flow, the data fields returned (prices, context window, flags), the provider coverage, and all filter names. Only minor ambiguities (query semantics, unit conventions, response shape after payment) are left 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 carries the full burden, and it names all nine parameters (q, provider, free=yes, max_input_per_m, min_context, vision=yes, tools=yes, sort=input|output|context, limit<=100) with their enum values and the limit cap. Gaps remain: 'q' and the units of min_context/max_input_per_m are not spelled out.

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?

The description states a specific resource (AI model list prices per 1M tokens, context window, capability flags) and scale (~3,000 models across named providers), so the agent knows exactly what data is behind it. It does not explicitly differentiate from siblings like llm_pricing_sample, llm_cost, or dump_llm_pricing, leaving some routing ambiguity.

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 description explains the calling mechanism ('returns the exact HTTP request and x402 payment requirements; pay with any x402 client'), which is useful operational guidance. However, it never says when to prefer this paid tool over the free sample or llm_cost sibling, nor any exclusions.

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