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

Goes well beyond the annotations: discloses that this is a separately authenticated relay requiring a Bearer key, an enabled backend operation and an accepted payment mode, and explains the x402 vs prepaid cost model. Crucially it states 'Admission is not delivery' and prescribes polling skavio_agent_job_status plus retrieval via skavio_agent_job_result and SHA256 verification — behavior an agent could not infer from readOnlyHint/idempotentHint alone.

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 purpose and the sibling routing, which is exactly what an agent needs first. It is dense with auth/payment boilerplate in the middle, but every sentence carries actionable information; the slight redundancy with the schema's idempotency wording is the only waste.

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?

There is no output schema, and the description compensates fully by explaining that the result is not returned inline — you must poll job status, fetch the result, and verify SHA256. Given the async job pattern and payment/auth complexity, this is complete enough for an agent to call and consume the tool correctly.

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 schema already documents units, data_base64, payment_mode and idempotency_key, which sets a baseline of 3. The description adds operational meaning by tying idempotency_key to a recovery workflow ('Retry with the SAME idempotency_key and inputs to recover, not a new job') and by framing payment_mode as quote-vs-credits, which is more than a restatement. It adds nothing for the legacy units param, keeping it below a 5.

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 ('Extract embedded selectable text from a PDF supplied as base64') and immediately delimits scope with the 'embedded selectable text' qualifier. It names the sibling tools document_ocr and invoice_extract as the alternatives for other input types, so an agent can pick correctly without opening a schema.

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?

Gives explicit when-to-use ('text-layer PDFs') and when-to-use-something-else ('document_ocr when pages are scanned images, invoice_extract for structured invoice fields'). It also covers operational guidance: retry with the SAME idempotency_key, no anonymous execution, and the poll/retrieve flow after admission.

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