Audit translations

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds that output volume can be controlled via checks, but says nothing about result grouping, performance on large projects, or how the four finding types are structured in the response.

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?

Two tight sentences with zero filler: the scope ('Project-wide health check') is front-loaded, the four findings follow, and the closing scoping tip ends the description. Every clause carries information.

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?

For a read-only audit with no output schema, the description adequately conveys what kinds of findings are returned and how to limit them via `checks` and `limit`. It stops short of describing the shape or grouping of the returned findings, which an agent may still need to plan around, but nothing critical for invoking it 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?

Schema coverage is 100%, so the baseline is 3, but the description genuinely expands semantics beyond the schema: it explains what 'missing' means (keys absent in some locale relative to the base locale), what 'code' means (used in code but untranslated), and what 'unused' means (never referenced in code) — none of which the bare enum list conveys. The baseLocale relationship is also clarified.

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 a specific verb+resource ('Project-wide health check') and enumerates the exact four findings it produces: missing keys vs base locale, placeholder mismatches, code-used-but-untranslated keys, and unused keys. This enumeration maps directly onto the `checks` enum values and clearly separates the tool from read-oriented siblings like i18n_search_keys or i18n_get_translations.

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 closing sentence 'Choose checks to keep the response small' is a usage hint for scoping the response, and the 'vs the base locale' phrasing implies the comparison context. However, it never says when to reach for this tool versus siblings (e.g. i18n_search_keys or i18n_key_references) or when not to run it, leaving the choice largely to inference.

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