Estimate the cost of a chat request

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

The description adds significant context beyond the annotations: 'no state changes and no external calls,' 'computed locally from server pricing config,' 'free, no payment, no authentication required,' and 'repeated calls with identical inputs return identical results.' These details clarify side effects, network behavior, and prerequisites, which annotations alone do not convey. No contradiction with the readOnly/idempotent/destructive hints.

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 description is three dense, well-structured sentences with no filler: what it does, safety/behavior, and invocation guidance. It front-loads purpose and money implications before diving into behavioral details, and every clause adds operational value.

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?

Given there is an output schema, the description need not detail return values. It covers the required input contracts (model vs mode, messages, max_tokens), the behavioral/read-only path, the cost/auth implications, and points to related tools (chat_completions, list_models). Nothing an agent needs to call it correctly on HTTP is missing.

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% with each property described, so the baseline is already strong. The description goes further by defining mode values ('auto = cheapest model fitting the context, eco = cheapest available, premium = best model') and by clarifying the relationship between model and mode: 'one of two required — if both are sent, model wins.' This resolution semantic is critical and not fully captured by the schema's anyOf.

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 uses a specific verb and resource: 'Estimate the USDC cost of a chat completion request before paying.' It clearly scopes what the tool does and implicitly distinguishes it from chat_completions (the paid execution tool) and list_models (the model-listing tool), reducing ambiguity without even checking sibling schemas.

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 explicitly says when to use this tool: 'Use this tool to check the exact price for a given model/mode, messages, and max_tokens before calling the paid chat_completions tool.' It also gives usage constraints: one of model/mode required, mutually exclusive, and 'if both are sent, model wins.' This tells an agent exactly when and with which arguments to invoke it.

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