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

Annotations already provide destructiveHint=true, readOnlyHint=false, and idempotentHint=false. The description adds valuable context about credit costs (1 credit per result, no charge for already-completed rows) and that 'Retry generations can cost additional generation credits.' It also notes the tool is 'built for scale' and clarifies behavior for large batches. While it doesn't explicitly state destructive outcomes, the credit/retry details give additional transparency beyond annotations.

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 longer than typical but every sentence carries information: purpose, usage triggers, exclusions, workflow, costs, scale guidance. It is front-loaded with the core purpose and remains organized and scannable. A slight deduction for being a bit verbose, but it earns its length.

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?

No output schema exists, so the description should hint at expected outcomes. It does this indirectly by directing the user to call read_generation_result_qa afterward, implying the tool queues QA rather than returning results. It also covers costs, retries, scale, and when to avoid auto-invocation. Missing an explicit statement of what the tool returns (e.g., queue status or IDs), but the follow-up instruction mitigates this gap.

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 description coverage is 100%: both generation_result_ids and max_qa_retries have descriptions that already mention credit costs and retry implications. The tool description repeats those cost mentions but does not add new semantic meaning beyond the schema. Since schema does the heavy lifting, 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 states it is the 'Default tool for generation-result QA' with a specific verb (queue/run QA) and resource (generation results). It clearly distinguishes itself from view_image by explicitly forbidding substitution unless the user asks for manual visual critique. This is a specific verb+resource with sibling differentiation.

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 when-to-use criteria ('whenever the user asks to QA, quality check, validate, review, inspect for defects, approve/reject, or assess already-created generation results'), a clear workflow ('First identify the numeric generation_result_ids, then call this tool, then call read_generation_result_qa'), and explicit exclusions ('do not substitute view_image', 'do not queue QA on your own initiative' for small batches). This fully addresses when and when not to use.

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