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 well: it discloses the file is not mutated, that numbers are checksum-validated (SNILS, INN, cards), and that scanned pages without text are reported separately. It omits any auth, rate-limit, or file-size constraints, keeping it from a 5.

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?

Content is front-loaded with the core action first, then per-parameter notes, then the return shape. It is dense but every clause adds information; only the return-shape paragraph is somewhat verbose given an output schema already exists.

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 3-parameter detection tool with no annotations and an existing output schema, the description covers what the tool does, what it does not do to the file, which parameters exist, and even how the output boxes feed into redact_pdf. Nothing essential for correct invocation is missing.

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%, so the description must compensate and does: file_url is defined as a public PDF URL, kinds enumerates the accepted values and the default-all behavior, and words explains custom terms with the 3-character minimum. All three parameters gain meaning beyond the bare schema.

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 ('Находит персональные данные в PDF') plus the key constraint that the file is not modified, which separates it from mutating siblings like redact_pdf or edit_pdf. An agent can identify the operation 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?

It gives a clear usage context — detection of personal data with checksum validation, file left unchanged — and points to the downstream workflow by noting that returned boxes can be passed to redact_pdf as areas. It does not explicitly contrast itself with alternatives like ocr_pdf or image_to_text, so it stops short of a 5.

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