List available models and prices

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

The annotations already declare readOnly, idempotent, and non-destructive behavior, and the description adds substantial context beyond that: no authentication or payment required, arguments are ignored, data comes from local config, repeated calls return identical results, and there is no filtering or pagination. This gives an agent a complete behavioral picture with no surprises.

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?

Every sentence adds distinct value: scope, authentication/read-only/idempotency, parameter handling, absence of filtering, recommended usage, API equivalence, and exclusions. Although it is a longer description, it is tightly packed with actionable information and remains highly scannable because each sentence addresses a separate concern.

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 zero parameters, a trivial input schema, and a true output schema, the description fully addresses everything an agent needs to know: cost model, authentication, side effects, behavior with no arguments, and clear routing versus sibling tools. There are no meaningful gaps in context.

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?

There are zero parameters, and the description expands on this by explicitly stating that the input schema is an empty object and that any arguments passed are ignored. This is more informative than simply inheriting the schema. A 0-parameter baseline is already strong, and the extra clarity about ignored arguments earns a slightly higher score.

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 verb and resource: 'List available models and their prices.' It clearly distinguishes itself from siblings by stating it does not generate text (chat_completions) and does not estimate request costs (get_price_estimate). The purpose is unambiguous and fully captures the tool's scope.

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 gives explicit guidance on when to use this tool: 'Use this tool to inspect models and prices before calling the paid chat_completions tool.' It also explicitly says when not to use it, naming the alternatives for text generation and cost estimation. This leaves no ambiguity about tool selection.

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