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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses the async requestId flow, polling via check_job_status with jobType='translate-epub', temporary 6-hour download URLs, engine selection by language, per-character pricing, the create_payment prerequisite, re-pricing at execution, and short-pay refunds. This goes well beyond a basic summary.

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 description is dense but every sentence earns its place: purpose, fidelity guarantees, language/price model, async flow, payment requirements, and edge-case refunds are all covered. The main action is front-loaded, and the rest follows a logical order from call to polling to payment details.

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 no output schema and no annotations, the description covers everything an agent needs to invoke the tool correctly: required inputs, async behavior, how to poll, where to fetch the result, how to pay, and what to do about re-pricing. The only minor omission is guidance on error handling, but the description is unusually complete for a complex paid async tool.

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%, so the baseline is 3. The description adds meaningful semantics beyond the schema by stating that paymentId must be a valid paid payment ID and that targetLanguage must equal the language used when creating the payment. It also ties the characterCount used in create_payment to the tool's pricing model, which helps the agent plan the payment step.

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 opening sentence, 'Translate a whole EPUB into another language and get an EPUB back,' states a specific verb, resource, and output, clearly distinguishing this tool from siblings like translate_text and epub_to_audiobook. The added detail about preserving markup, translating the TOC, and retargeting package language further pins down the exact scope.

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?

The description makes the usage context clear: whole-book EPUB translation with markup preservation, async polling, and Lightning payment. It references translate_text only for rate comparison rather than explicitly saying 'use this instead of translate_text for EPUBs,' so it stops short of explicit when-not guidance, but the context is strong enough for an agent to select it correctly.

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