check

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

With no annotations, the description carries the full burden and correctly conveys that output is findings with a time and a DSL fix, plus an OK signal when clean. However it never states whether the check is read-only/idempotent, whether it can be slow or costly (analysis of rendered media), or whether the DSL fix is applied or merely suggested.

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?

Front-loaded verb+object, then a compact colon list of check categories, closing with the success condition. No filler sentences and nothing redundant.

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?

An output schema exists, so return-value explanation is not required, and the description still notes the finding shape and the OK result. The remaining gap is operational context — prerequisites, read-only nature, and cost — which is modest for a single-parameter QA tool.

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?

There is one parameter (version_id) and schema coverage is 0%, so the description must compensate. 'A rendered version' loosely ties the argument to a rendered version object, but gives no format hint (ID vs name) beyond what the self-explanatory parameter name already implies.

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 action (QA a rendered version) and enumerates the exact defect classes it looks for, so an agent can tell it apart from 'render' or 'diff'. It does not name siblings, but the scope is unmistakable.

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?

Usage is only implied by 'a rendered version', which suggests post-render inspection, and by 'Returns OK when clean', which hints at a pass/fail gate. No explicit when-to-use, no prerequisites (must a render exist first?), and no alternatives such as 'diff' for version comparison.

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