validate

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

Annotations already declare readOnlyHint=true, and the description reinforces this with 'without changing it'. It adds genuinely useful behavior beyond the annotation: the two-phase judge-then-resubmit flow with llm_judgements, and that deterministic and judged results are reported separately.

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 lead sentence is front-loaded and every subsequent clause (sections, workflow, fix path) earns its place. The inline 'section:' formatting and leading whitespace are slightly rough, but the content is dense and purposeful rather than padded.

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 values need no explanation, and the description covers the section taxonomy, the interactive judgement loop, and the fix path. For a three-parameter tool the only real omission is documentation of the 'path' argument.

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?

With 0% schema description coverage the description must carry the load, and it does well for two of three params: it enumerates the section values and spells out the llm_judgements object shape ({rule_id, field, outcome, note}) with the pass|warn|fail outcome domain. The required 'path' parameter is left entirely unexplained, a minor remaining 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?

The description gives a specific verb+resource: it reviews/validates the contents of steamworks.yaml (and translations) without modifying it. The 'without changing it' clause usefully distinguishes it from save_draft, though it doesn't explicitly contrast with other diagnostic siblings like gap_report or scan_project.

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 clearly states the use case (review before changing) and enumerates the section choices ('store', 'achievements', 'localization', 'all'), then describes the two-phase workflow for store text. It also points to save_draft(strategy='revision') for fixes, giving a clear alternative, but stops short of explicit when-not-to-use guidance.

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