Legal Check

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new context beyond them: the check is offline/static rather than against live pages, and it sketches the return shape ({ok, problems}). It stops short of describing pagination or problem-entry detail, which the output schema presumably carries.

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 terse lines, front-loaded with the outcome ('what still blocks publishing'), followed by usage and return shape. No filler 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?

With annotations covering the safety profile, a full schema description, and an output schema, the description only needs to add routing and behavioral context — which it does. Nothing an agent needs to invoke this correctly 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?

Only one parameter, app_dir, and schema description coverage is 100% with an example path given in the schema itself. The description adds no syntax or format information beyond the schema, so the baseline 3 applies.

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 (list) and resource (blockers for publishing legal pages), then enumerates the concrete problem classes it reports: placeholders, unrendered blocks, missing languages. That specificity lets an agent distinguish it from the sibling legal_verify and legal_render without opening 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?

Explicitly names the trigger condition ('after legal_render, offline') and routes the agent to the alternative for the other case ('For checking the live pages use legal_verify'). Both the when and the when-not are covered.

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