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

Annotations already declare readOnly, idempotent, and closed-world. The description adds meaningful behavior beyond that: a privacy constraint (send totals, never prompts or keys), the date-suffix normalization rule, and the unknown-model fallback returning suggestions.

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 core action, then constraints, then the practical how-to. Dense and mostly waste-free, though the embedded Claude Code instructions are lengthy enough to slightly dilute the primary purpose.

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 must convey results, and it does: costs at list and cheapest seller, the saving, and suggestions for unknown models. Combined with the privacy and matching rules, an agent has enough to call it correctly.

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 only 50%, so the description must carry weight. It explains the model-name matching rule and the notion of per-model/per-month totals, but says nothing about current_seller or the individual token-type fields (cache write, 1h cache, etc.). Baseline 3 is appropriate.

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 — price the user's real token usage — and enumerates the exact outputs (official list price, cheapest verified seller, saving). This clearly separates it from siblings like estimate_cost and get_model_prices.

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?

Gives real context: send totals only, model names must match easiapiai.com, unknown names return suggestions, and one concrete recipe for gathering totals in Claude Code. It doesn't explicitly state when to prefer this over estimate_cost, so it stops short of a 5.

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