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

The description adds substantial behavioral detail beyond the annotations: asynchronous execution, cost/credit implication, mandatory user approval, idempotency retry behavior, and the fact that disconnecting does not cancel the job. These are not captured by the readOnlyHint/openWorldHint/idempotentHint/destructiveHint annotations and add real value for the agent. No contradiction.

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 distinct information: the core purpose, the approval/retry guidance, and the disconnection caveat. No filler, and the most critical information (submission + credits) is front-loaded. Efficient and well-structured.

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 7-parameter tool with no output schema and very low schema coverage, the description omits critical operational details: what the tool returns (e.g., job ID), how to track progress, the exact meaning of confirmed=true, and how parameters like pages and output_formats behave. It also doesn't point to sibling tools like get_translation_results for status checking. The description covers usage guidelines well but leaves agents guessing about invocation and result handling.

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 only 14%, so the description must compensate, but it does not explain any parameter meaning. It mentions idempotency_key generically but doesn't clarify required fields like file_id, target_language, or the confirmed boolean, nor optional ones like pages or output_formats. The description adds no parameter-level detail, leaving agents to infer from names alone.

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 action (submit an asynchronous PDF translation) and the resource, and notes it uses the user's website credits. This clearly distinguishes it from siblings like estimate_translation (estimation) and the various get_* retrieval tools, so an agent can identify its role immediately.

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?

Explicitly instructs to ask for user approval after showing estimated cost, implying a prerequisite step (likely estimate_translation). It also advises reusing the same idempotency_key and parameters after a timeout, which is a clear retry guideline. It doesn't name alternatives directly but provides sufficient contextual direction.

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