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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds behavior annotations don't carry: it is free, it is a live provider quote, and the price is only valid for the exact settings supplied. It still says nothing about latency or failure modes when a model/settings combination is invalid.

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?

Three tight sentences, front-loaded with what it returns, and every clause carries actionable information (settings scope, free, downstream maxCredits use). No filler.

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?

With no output schema, the description correctly explains the return ('live credit price') and what to do with it, and it flags the nested inputs object implicitly via the settings list. For a 5-param nested tool it could say more about required vs optional inputs and invalid-setting behavior, but nothing essential 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 only 40% across 5 params, but the description names the settings that drive the quote (resolution, duration, audio, attached media length) and explains the output's use as maxCredits. It adds no guidance on mode, prompt, or how category interacts with the other fields, so it only partially compensates for the coverage gap.

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?

States a specific verb+resource ('Live credit price for one video, image or motion-control generation') and pins the scope to 'these exact settings', which separates it from the sibling get_credits (account balance). An agent can tell immediately this is a per-generation cost quote, not a balance check.

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?

Gives clear when-to-use ('Use before expensive video jobs') and a concrete downstream workflow ('tell the user the cost, and pass the credits as maxCredits to the create tool'). It doesn't state exclusions or contrast with get_credits, so it falls just short of a 5.

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