metadata_ai__draft_translation

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

Annotations already mark readOnlyHint=true, and the description adds valuable behavioral detail: it will not decide which languages need updating, output is a draft for human review, and keyword results are non-final starting points. This goes well beyond the annotation without contradicting it.

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?

Three sentences, each carrying a distinct piece of information, and the core action is front-loaded. It is appropriately compact, though the phrase 'instruction for you to draft it' vs 'returns a draft' adds a slight ambiguity that keeps it from a perfect conciseness score.

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 no output schema, the description tells the agent what to expect (source text plus instruction, and a draft for a person to read) and what not to do (write, infer locales, treat keywords as final). The parameter schema covers the remaining details, making the definition complete for an AI agent deciding to call it.

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 adds meaning for fields like 'keywords' by explaining that a keyword draft is a starting point, not a finalized answer. It also reinforces the to_locales constraint that translation only happens for explicitly requested locales.

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 identifies a specific deliverable (source store text plus drafting instruction), defines the action as drafting, and distances itself from applying changes or auditing staleness. This clearly separates it from siblings like metadata_ai__apply_localizations and metadata_ai__audit_localizations.

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?

It gives explicit context for when the tool should be used: only for locales the caller requests, never for the tool to infer stale languages, and as a human-readable draft rather than a committed write. It does not name exact alternative tools, but the exclusions are clear enough to route an agent.

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