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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantial behavior: data residency (processing stays on AIProcurement.club), no retention, no Gateway memory or external inference, no invoice/idempotency key, and an explicit untrusted-data/OCR-review warning. These are exactly the operational facts an agent cannot get from the structured fields.

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?

Purpose and scope are front-loaded in the first two sentences, and the limits/security facts follow in a compact block. The telegraphic, comma-spliced style is dense but nearly every clause carries a distinct constraint; a little restructuring would improve scanability.

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?

With no output schema, the description still signals the return shape ('preserving exact page citations and missing fields'), and it covers limits, auth, residency, and OCR behavior for a 3-parameter tool. The only real omission is any hint of result ordering or how mismatches are reported.

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 carry the load, and it does for the two hardest parts: the ocr enum semantics ('auto handles empty-text pages, always handles mixed image/text', English OCR) and the files constraints (up to 6 files, 512 KiB combined, 12 pages/PDF, 32k chars/document). Only orderId is left unexplained, which is a minor gap given its obvious role.

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?

The opening sentence names a specific verb (compare) and enumerates the exact fields compared (Supplier, Total, Currency, ISO Delivery date) plus the output trait (page citations, missing fields). That is far more specific than the sibling names alone, though it never explicitly contrasts itself with procurement_order__documents or procurement_purchase_order__evidence.

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 when-not ('No approval or financial reconciliation') and a prerequisite ('Requires agent:read'), which is useful routing context. However, it never states when to pick this over the closely named siblings such as procurement_purchase_order__evidence or procurement_order__documents, leaving the main selection decision to inference.

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