Missing and broken translations

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

Consistent with readOnlyHint=true ('Read-only'). It adds genuine behavior beyond annotations: warnings are listed but never fail the gate, and it distinguishes error-class findings from warning-class findings (extra, divergent, outdated, incomplete plurals). It doesn't discuss output shape or volume, but an output schema exists to cover that.

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 with the action and the main findings, and every clause carries substantive information. The cost is a very long run-on first sentence with nested parentheticals that makes the enumeration harder to scan than it needs to be.

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 only two optional params, a readOnly annotation, and an output schema covering return values, the description is sufficient to call the tool correctly. The one gap is the relationship to overlapping diagnostic siblings (verbaly_doctor, verbaly_status), which is not addressed.

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 schema carries parameter documentation and baseline would be 3. The description still adds real meaning by explaining that drafts optionally includes machine translations awaiting human review, giving the 'why' behind the flag; `root` is left entirely to the schema.

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?

Opens with a concrete verb+resource ('List missing translations, unknown keys...') and enumerates the exact defect classes the tool surfaces, including render-breakage categories. It anchors the tool to a known artifact ('the same gate `verbaly check` runs in CI'), so an agent can distinguish it from siblings like verbaly_status or verbaly_doctor.

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?

Establishes clear context for use — post-extract/translate validation equivalent to the CI gate — and notes the optional drafts mode. It never explicitly names alternatives or states when to prefer verbaly_doctor or verbaly_status instead, so the agent must infer sibling routing.

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