metadata_ai__audit_localizations

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

The readOnlyHint annotation is present, and the description goes beyond it by specifying the audit's scope, the kinds of issues reported, and the no-mutation guarantee. It does not describe response structure or edge cases, but the annotation lowers the burden and the description adds meaningful behavioral context.

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 two sentences with no filler: the action and resource are front-loaded, concrete examples are packed into the em-dash list, and the read-only clarification is isolated for emphasis. Every sentence contributes.

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?

This is a simple two-parameter tool with one required parameter, full schema coverage, and a read-only annotation. The description provides enough behavioral context for an agent to select and invoke it correctly, though the exact report output format is not specified since no output schema exists.

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?

The input schema already documents both parameters thoroughly, including the version default, so the description does not need to add parameter syntax. It adds some conceptual context by tying the audit to 'store text' and 'every language,' but that does not go beyond the schema's coverage.

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 opens with a specific action ('Compare an app version’s store text... and report') on a concrete resource, then lists exact defect categories: empty descriptions, blank keywords, and language-coverage gaps. It also clarifies what the tool does not do, setting it apart from sibling apply/draft tools.

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 clearly frames the tool as a read-only audit and explicitly states it 'reports and stops' and 'never fills anything in,' which signals when to use it and when not to use it. It does not name sibling alternatives like metadata_ai__apply_localizations, but the context is strong enough for an agent to route correctly.

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