Skip to main content
Glama

Missing and broken translations

verbaly_missing
Read-only

Lists missing translations, key collisions, and translations that drop params, rich tags, or plural blocks in a JavaScript i18n project; read-only and can include machine translation drafts.

Instructions

The gate verbaly check runs in CI, as lists: missing translations, unknown keys, keys written with two texts (collisions: every place shows the first text) and translations that cannot render what the source renders. A dropped {param}, a lost rich tag or a flattened plural block is that last kind. Warnings never fail the gate and are listed too: an incomplete plural set for the locale, keys only a translation has (extra), texts the code and the source catalog disagree on (divergent: the text in the code ships) and translations written for an older source text (outdated). With drafts set, it also lists the machine translations awaiting review. Read-only. For counts use verbaly_status, to review drafts with their source text verbaly_drafts, and for setup problems verbaly_doctor.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "verbaly_missing"
  }
}

Input Schema

NameRequiredDescriptionDefault
rootNoProject root holding verbaly.config (defaults to the server working directory)
draftsNoAlso list machine translations awaiting human review

Output Schema

NameRequiredDescriptionDefault
okYesWhether `verbaly check` would pass (warnings never fail it)
extraYesKeys only a translation has; files are where the code reads one, which the source language then shows as the key itself. Never fails the gate
brokenYes
missingYes
unknownYes
outdatedYesTranslations written for an older source text: rewrite them, or a human keeps them with verbaly review --approve. Never fails the gate
divergentYesThe source catalog says one text and the code another: the code's text ships. Never fails the gate
collisionsYesOne key, several texts: every place shows the first site, so it fails the gate. Give each text its own key
unreviewedYes
stateProblemNoThe state file could not be read, so outdated translations are not listed

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation it discloses the full severity model: which categories are hard failures versus warnings, that warnings never fail the gate but are still listed, and that drafts only surface with the flag set. That taxonomy – especially 'collisions: every place shows the first text' and 'divergent: the text in the code ships' – tells the agent what each result actually means, which no structured field conveys. The 'Read-only' sentence merely restates the annotation but does not contradict it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every clause carries real information and the sibling routing is front-loaded at the end where an agent will look, but the text is one long run-on with broken grammar ('runs in CI, as lists: ...') and packs four failure types and four warning types into a single unbroken block. Bullet-style grouping of warnings versus failures would have made it far easier to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, schema-covered, output-schema-backed reporting tool this is nearly complete: it defines every result category and points to the right alternatives. The only omissions are why/when to invoke it outside CI and any mention of the `root` parameter's effect on which project is inspected.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented, and an output schema exists. The description reinforces `drafts` ('With drafts set, it also lists the machine translations awaiting review') but adds no syntax or default information beyond the schema, and says nothing about `root`. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates exactly what the tool reports: missing translations, unknown keys, collisions, and translations that cannot render the source (dropped {param}, lost rich tag, flattened plural), plus the warning categories. The resource is unmistakable and it is clearly not verbaly_status or verbaly_drafts. The one weakness is that the verb is implied by 'as lists:' – it never plainly says 'this tool returns the list of...', and 'The gate `verbaly check` runs in CI' momentarily reads like it is describing a CLI command rather than this tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly routes the agent to three alternatives with the condition that selects each: verbaly_status for counts, verbaly_drafts to review drafts with their source text, verbaly_doctor for setup problems. What it lacks is an explicit trigger for this tool itself (e.g., 'call after editing config or before committing'), which is only implied by the CI-gate framing.

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