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

With no annotations, the description carries the full burden and does so thoroughly: quotes are verified against the document text, key dates and risk flags are computed, the document is not stored, pages beyond 80 are rejected, and cost (€0.2 per contract, billed per started ~20 pages via the Bearer API key) is spelled out. This is far beyond the minimum.

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 capability and covered clause types, then behavior, then parameters. Dense but largely waste-free; the long parenthetical clause list and the compact parameter run-on make it slightly harder to scan, 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 return values need not be re-explained, and the description still summarizes the payload (summary, typed values, verbatim quotes with page). Pricing, auth, retention, size limits and parameter roles are all covered, leaving nothing an agent needs to call it 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 0%, so the description must compensate, and it defines all three parameters meaningfully: url for PDF/DOCX, text as the alternative, and language as the OCR language list with the default set. It stops short of stating that at least one of url/text must be supplied (required parameters is 0), which is an important semantic gap.

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 clauses from a contract document) and enumerates the 24 clause types covered, which distinguishes it clearly from siblings like invoice_parse, resume_parse and entity_extract. It also names the output shape (summary, typed values, verbatim quote with page).

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?

Usage context is implied through input formats and the 80-page limit, and cost/pricing is disclosed, but there is no explicit statement of when to use this versus generic tools such as pdf_text or entity_extract. No exclusions beyond the page cap and 'Not legal advice'.

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