localization_set

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

Annotations already declare non-readonly, non-destructive, closed-world execution, and the description layers on genuinely new behavior: three concrete rejection conditions (BBCode mismatch, >300-char short description, Valve store-text violations) and the draft/approval lifecycle. That is substantial disclosure beyond the annotation surface, though it does not address permissions or idempotency.

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 core action, then validation rules, then the approval caveat — no filler. The parenthetical syntax is dense but each sentence carries distinct 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?

An output schema exists so return values needn't be explained, and the description covers the mutation's semantics, failure modes, and the required follow-up approval step. The main remaining gap is the undocumented 'path'/'source' parameters.

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 0% for four parameters, so the description carries the full burden. It clarifies the shape of 'translations' ({key: text}) but says nothing about 'path', 'language', or the 'source' enum (generated vs user), leaving over half the parameters undocumented anywhere.

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 and resource ('Save translations') and even sketches the payload shape ('{key: text}'), which cleanly separates it from read-side siblings like localization_status and localization_pending. It stops short of explicitly naming an alternative, so it falls just below the top score.

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?

Implies clear context: writes go in as drafts that only become live after the user approves via approve_fields, which tells the agent where this tool sits in the workflow. It does not state when to prefer this over set_field or state any preconditions, so not a 5.

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