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

Annotations declare readOnlyHint, openWorldHint, destructiveHint=false and idempotentHint=false; the description goes beyond them by explaining *why* it is non-idempotent — every call is charged ($0.01 via x402 USDC or card key, first 25 free, failed calls free) so repeats cost money. That is exactly the kind of cost/auth context annotations cannot convey, and it reinforces 'reads or computes only and changes nothing' consistently.

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?

Front-loaded with the verb and dataset, then filters, then source, then usage, then billing — a sensible order with no filler sentences. The billing/access clause is dense and runs long, slightly blurring the main purpose on first read.

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, the description compensates by naming the returned fields (input/output price, context length, max output, modalities, computed call cost). For a 9-parameter, zero-required query tool, an agent has everything needed to call it and interpret the response.

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%, so the schema already documents all nine parameters; the description nonetheless clarifies the coupling between inputTokens and outputTokens (they estimate the cost of your call) and restates the filter/sort axes in task terms. It adds modest but real meaning above baseline.

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 — 'Compare the API prices of about 450 LLMs' — and enumerates the concrete data returned (USD per million input/output tokens, context length, max output, modalities, per-call cost). The provider list and 'OpenRouter's public model list' source make it unmistakably distinct from siblings like crypto_price or units_convert.

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?

'Use to pick the cheapest model that fits a job' gives the decision context explicitly, and the description lists the filter/sort axes that select among alternatives. It adds a worked example ('q=llama') and names the sibling-free workflow, leaving little to infer.

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