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

With no annotations, the description carries the full burden and does well: it discloses the full pipeline, enum-like outcomes (accept/review/reject with reasons), a pricing model ($0.012 USDC per call via x402), and a critical caveat that this is heuristic triage, not verification. It omits failure modes (unreadable PDF, unreachable URL) and auth/payment flow details, keeping it at 4 rather than 5.

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 description is front-loaded with purpose and output, and the example output is dense with information that would otherwise be missing (no output schema). It is slightly dense and packs pricing, caveats, and example into a short block, but no sentence is wasted.

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 one-parameter tool with no output schema, the description supplies the missing return shape via a concrete JSON example, explains the decision semantics, and discloses cost and limitations. It stops short of describing error behavior or latency, which prevents a perfect score but leaves an agent well-equipped to call it.

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 100% and the single 'url' parameter is already documented as 'Public PDF or image URL of the invoice.' The description restates that the URL must be a PDF or image but adds no new format, size, or accessibility constraints beyond the schema. Baseline 3 applies.

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 description states a specific verb and resource ('Invoice intake... PDF or image URL in, one decision-ready JSON out') and makes the composite nature explicit by naming the sub-steps (text extraction, email risk check, domain lookup). This clearly distinguishes it from atomic siblings like document_extract, email_check, and domain_lookup.

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 targets 'AP agents' and adds a useful when-not caveat: 'Heuristic triage, not bank verification.' It does not explicitly route to or exclude sibling tools (e.g., 'use document_extract for non-invoice documents'), but the invoice-specific framing is strong enough for most selection decisions.

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