Price a generation without paying

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

The description adds key behavioral traits beyond annotations: it costs exactly zero, a rejected proposal is never charged, and it involves submitting and rejecting a request. The readOnlyHint annotation is consistent with this, and the description provides valuable context about the transient nature of the proposal.

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 two sentences, each carrying weight: first explains the action, second explains the benefit and use case. It is front-loaded with the critical info and wastes no words.

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 the tool's simplicity (1 param, no output schema, clear annotations), the description fully explains the workflow and outcome. It covers what the tool does, how it works, and why to use it, leaving no gaps.

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?

The lone parameter 'prompt' has full schema coverage (100%) with maxLength and minLength constraints. The description adds that the prompt is what you intend to run, but this adds little beyond the schema description. 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?

The description clearly states the tool's purpose: submit a request, read the quoted cost, then reject it to avoid charges. It uses specific verbs ('submit', 'read', 'REJECT') and identifies the resource (cost estimation). This distinguishes it from siblings like flow_budget or flow_ledger, which deal with budget management, not zero-cost estimation.

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 provides explicit context: 'Use this to confirm the project's model tier before committing to a batch.' It implies when to use (pre-commitment check) and that it costs zero. However, it doesn't explicitly mention when not to use it or list alternatives, but the sibling tools are available for actual generation.

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