Identify translation keys added, modified, or deleted in a source locale file since the last sync, so agents can review pending changes before translation.
Preview what translation keys have been added, modified, or deleted in the source file relative to the last sync (cache-based)
| Name | Required | Description | Default |
|---|---|---|---|
| source_file | No | Source file to check for changes | en.json |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden. 'Preview' conveys non-destructiveness and 'cache-based' usefully signals that results depend on cache freshness, but it says nothing about what happens on a stale/missing cache, whether auth is required, or whether the output is a flat key list or grouped by change type.
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?
A single sentence with the operation, change taxonomy, and comparison baseline front-loaded, plus a tight parenthetical for the cache qualifier. Nothing is redundant or padded.
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 one-parameter, no-annotation, no-output-schema preview tool, the description covers the essential operation and the three change categories an agent needs. The main remaining gap is that the shape of the preview result (counts vs. key lists) is unspecified, which matters for a tool whose whole output is the payload.
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 description coverage is 100% and the single enum parameter is fully documented, so the baseline is 3. The description refers only generically to 'the source file' and adds no detail beyond the schema — it does not mention that only en.json and en-b2b.json are valid or what the default is.
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 (preview), resource (translation key changes), and the three change categories (added/modified/deleted) plus the comparison baseline (last sync). The '(cache-based)' qualifier implicitly distinguishes it from the sibling preview_git_changes, but it never names that sibling explicitly, so the differentiation requires inference.
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?
Usage is only implied by the 'relative to the last sync (cache-based)' phrasing — an agent can infer this is for cache-state checks versus git-state checks. There is no explicit statement of when to prefer this over preview_git_changes or sync_translations, and no prerequisites or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.