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

Beyond readOnlyHint/destructiveHint, it explains that estimates do not reserve price or authorize generation, notes environment pricing differences (staging vs production), describes how technical failures follow the job and refund state, and clarifies that creative attempts are billable while technical failures are not – all critical safety and side-effect context.

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 long (~300 words) but every sentence carries meaning – usage triggers, exclusions, parameter conditions, and behavioral caveats. It is front-loaded with the core function and organized from general to specific, with no fluff, though it could be tightened slightly.

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?

For a read-only estimation tool, it covers prerequisites (get_model_details), environment differences, parameter constraints, and exclusions. It omits explicit return-format details, but the absence of an output schema and the tool's purpose make the expected response (an estimate) inferable.

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% already, but the description adds actionable conditional logic: omit settings.audio when not optional, omit aspectRatio when mode.aspectRatios is empty, and separate base production from creative-attempt allowance. These go beyond the schema's declarative descriptions and help the agent construct valid requests.

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 opens with a precise statement of purpose: 'current pricing estimates of concrete video production proposals.' It names specific scope (single- or mixed-model shots, clip counts, creative attempts) and explicitly lists non-uses ('invent the creative plan', 'reserve a price', 'create a generation quote', 'inspect the wallet', 'spend funds'), which clearly distinguishes it from generation and wallet tools.

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?

It starts with 'Use this when' providing a clear trigger, and gives explicit exclusions. It advises comparing proposals on the same assumptions before calling an alternative cheaper/lower-cost, implying there are other pricing tools, though it doesn't name them. It also directs validation via get_model_details, which orients the agent to prerequisites.

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