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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuinely beyond-annotation context: the deferred-payment model (download URLs only appear once complete AND payment settles, failed jobs report charged=false, and polling is free even though generate calls are paid). This is valuable behavioral detail.

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?

A single dense paragraph that front-loads the purpose and the key FREE distinction before covering return behavior, failure cases, and lookup methods. Slightly redundant in restating free-ness ('FREE:' prefix plus '[Free — no payment required.]'), but otherwise efficient with no wasted sentences.

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?

Complete for a read-only poll tool with no output schema: it covers return content (status/progress, download URLs after payment settles, charged=false on failure) and both lookup paths. The 0-required, 3-optional param ambiguity is resolved by the description. The only minor gap is not describing the shape of the progress/status values, which is acceptable without an output schema.

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% with parameter descriptions for payer, job_id, and idempotency_key, so the schema already documents all parameters. The description adds marginal value by clarifying the relationship between them (idempotency_key + payer used as fallback when job_id is lost), but this mostly restates what the schema conveys. 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?

States a specific verb and resource ('poll a generation job submitted by the paid generate tools') and precisely distinguishes this read/status tool from the payment-required sibling generate tools. The purpose is unmistakable and differentiates the tool from its siblings without opening any schemas.

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 usage context: poll jobs produced by the paid generate tools, and explains the two lookup paths (by job_id, or by idempotency_key + payer as a fallback when job_id is lost). This tells the agent when and how to invoke it. It doesn't explicitly name exclusion cases, but the context is solid for a polling tool.

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