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

Goes well beyond the annotations: it names the required scope (agent:read), states that processing stays on AIProcurement.club with no retention, no Gateway memory and no external inference, and enumerates hard operating ceilings (6 files, 512 KiB combined, 12 pages/PDF, 20 pages/pack, 32k chars/document, 75k/pack). It also discloses OCR language/behaviour and adds a prompt-injection warning to treat source text as untrusted and review OCR output — exactly the behavioural context the readOnly/idempotent hints cannot convey.

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 purpose and free of filler, but the middle section is telegraphic to the point of ambiguity — 'no Gateway memory, external inference, invoice or idempotency key' reads as a fragment whose meaning is hard to recover. The long limit list is informative yet presented as an unstructured run-on rather than a scannable set of constraints.

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 read-only search tool with no output schema, the definition covers privacy, authentication, hard limits, OCR handling and trust caveats thoroughly. The remaining gap is the return shape — nothing says what a result contains (quote plus document id, page reference, ranking) or how limit interacts with the per-pack character cap.

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 carries the burden, and it only partly does: it explains the 'auto' vs 'always' ocr behaviour, the files constraints, and that orderId must be an exact labelled ID. It says nothing about the 'question' parameter (the core search input, up to 2000 chars) or about 'limit' (default 8, max 12), leaving two of five parameters undocumented anywhere.

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 ('Retrieve exact source quotes') plus the mechanism ('existing local keyword search'), and immediately rules out the neighbouring semantic/extractive behaviour with 'No semantic or generated answer'. That contrast is what separates it from procurement_document__extract and the other evidence tools without needing their schemas.

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 'no semantic or generated answer' clause implies when this tool is preferred (verbatim lookup rather than summarisation), and the orderId filter is described as an optional narrowing. But no sibling is named and no explicit when-to-use/when-not guidance is given, so the agent must infer the routing from the negative phrasing.

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