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

Annotations already cover read-only, closed-world, and idempotent behavior, but the description adds substantial context beyond them: it validates INN, KPP, BIK and account checksums, reconciles item totals against the grand total and VAT, returns empty fields rather than inventing values, and does not save the uploaded file. This is unusually rich behavioral disclosure.

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 purpose and key limitations are front-loaded, and the long field enumeration is justified because there is no output schema. The final English summary is slightly redundant after the fuller Russian text, but overall the description is dense and well-organized rather than wasteful.

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 there is no output schema, the description carries the burden of describing returned fields and does so thoroughly: document type, number, date, parties, bank details, line items, totals, VAT, and amount in words. It also covers validation behavior, missing-field behavior, and unsupported input types, leaving little an agent needs beyond the schema and annotations.

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 url, base64, filename, and include_text are already documented. The description adds a file-level constraint (text layer required) but does not explain parameter formats, alternatives between url and base64, or usage syntax beyond what the schema provides. Baseline 3 is appropriate.

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 (extracts) and resource (structured data from Russian PDF/DOCX documents), and enumerates the exact document types and fields covered. This clearly separates it from generation siblings like make_invoice/make_act and from the standalone validation/utility siblings.

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 clear context for use: Russian documents in PDF or DOCX with a text layer. It also states a key when-not condition: scans and photos without a text layer are not supported. It does not name alternative tools such as validate_requisites or amount_in_words, so it falls short of explicit alternative routing.

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