estimate_inference_cost

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

With no annotations provided, the description carries the full burden and does so well. It explicitly discloses non-mutating behavior ('WITHOUT making the call or touching balance'), the return structure, and authentication requirements. This gives the agent a clear safety profile and expectations.

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 dense yet efficient: the first sentence states the core purpose, followed by return format, parameter selection rules, usage timing, and authentication. Every sentence serves a distinct purpose with no fluff or redundancy.

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 no output schema, the description appropriately explains the return value fields. It also covers key contextual aspects: non-side-effect behavior, when to use, how to select parameters, and auth requirements. For a cost-estimation tool with 8 params, this is complete enough for correct invocation.

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?

Although the input schema has 100% coverage, the description adds critical meaning beyond individual field descriptions: it maps parameter sets to model types and instructs 'Provide only the units the model bills', resolving which parameters are relevant for which use case. This is essential semantic info not present in the schema.

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 clearly states a specific action ('Estimate the USDC cost of a Floe Inference call') with a specific resource (Floe Inference) and scope ('given model and usage vector'). It also distinguishes itself from sibling tools by emphasizing 'WITHOUT making the call or touching balance', making it unambiguous what this tool does and doesn't do.

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?

Provides explicit when-to-use guidance: 'Use BEFORE inference to decide gating.' It also gives parameter-selection guidance per model type (text/TTS/STT/realtime voice) and prerequisite auth information ('Requires any Floe API key'). This is comprehensive for choosing this tool over alternatives.

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