AI-translate screenshot texts (async job)

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

With no annotations provided, the description carries full burden. It mentions 'async job' but does not disclose side effects, how to check status, or error conditions. Missing details like whether existing translations are overwritten, or if there are rate limits.

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?

The single sentence is concise and front-loaded with the main action. However, it is too terse and sacrifices necessary detail for brevity. Still, no wasted words.

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?

Given the tool's complexity (async job, batch operation), the description is inadequate. No output schema is provided, and key aspects like result retrieval, idempotency, or impact on existing translations are omitted. The description leaves significant gaps.

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 50% (appId and force described, locales and variantId not). The description only says 'into the given locales' without specifying format or constraints. It does not explain 'force' or 'variantId' beyond the parameter name. The description fails to compensate for missing schema descriptions.

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 clearly states it starts an async job to translate all screenshot headlines/captions to given locales. It uses a specific verb 'start an async job' and resource 'screenshot headlines/captions', distinguishing it from siblings like 'translate_field' or 'update_screenshot_text' which handle individual items.

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?

No guidance on when to use this tool versus alternatives (e.g., for single screenshots use 'update_screenshot_text', for fields use 'translate_field'). The description lacks context for selecting this tool over siblings.

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