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

With no annotations, the description carries the full behavioral burden and does so well: no file retention ('not even temporarily'), no OCR, hard limits of 10 pages / 30,000 chars, a per-file price of €0.04, and the bearer-token billing model. These are exactly the operational facts an agent needs before incurring cost.

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 arrow-style opening is front-loaded with the payload and every subsequent clause adds a distinct constraint (privacy, OCR, limits, cost, auth). Slightly dense and telegraphic, but nothing is redundant.

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 the field list is a bonus rather than a necessity, and the cost and size constraints round out the picture. What remains unstated is how the URL is fetched (public vs authenticated), file-size limits, and the error shape when a scan is rejected.

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 the single url parameter, and the description only adds the tautological gloss 'url: resume url'. It doesn't clarify whether the URL must be publicly reachable, whether signed URLs work, or why the parameter is optional in the schema despite being needed to do anything.

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 names a specific verb and resource ('PDF or DOCX résumé → ...') and enumerates the exact output fields (name, contacts, links, summary, work experience, education, skills, languages). 'Résumé' is a distinct resource among siblings like invoice_parse, contract_clause_extract and pdf_text, so an agent can differentiate it without opening the 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?

The input format and rejection conditions (scans without a text layer) imply when this tool applies, but it never names alternatives such as ocr for scanned documents, pdf_text for plain text extraction, or doc_convert for format changes. The agent must infer routing rather than being told.

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