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

Beyond the readOnlyHint/openWorldHint annotations, it discloses determinism ('no model calls'), the size ceiling that gates the call (500,000 chars paid / 30,000 free), and the exact shape of each returned item including character offsets and section headings. Those are precisely the traits an agent needs before committing a large document.

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?

Four dense sentences, front-loaded with what is extracted and followed by provenance guarantees, determinism, limits, and input format. Nothing repeats the tool title or the schema, and each sentence adds a decision-relevant fact.

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 describing the returned fields (offsets, section headings, dates, money, percentages) and the provenance guarantee. Combined with the stated input constraints and determinism, an agent has everything needed 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 only 50%, so the description must carry weight for the undocumented 'text' parameter — and it does, specifying plain-text-only input and the character limits that constrain its value. The optional 'source' label is left to the schema, which already documents it, so the gap is minor.

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?

Names a specific verb (extracts) and enumerates the exact resource classes it returns: obligations, prohibitions, recommendations, deadlines, submission instructions and evaluation criteria, plus the input domain (tender, RFP, contract, policy text). This is clearly distinguishable from siblings like verify_citations or validate_json, which operate on outputs rather than source documents.

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 a concrete input precondition — 'Plain text input; convert PDFs first' — and states capacity limits that determine whether a call is viable. It does not name alternatives or state when not to use it versus verify_citations, which is the natural downstream step, so it stops short of the top band.

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