Classify AP exceptions

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

With no annotations provided, the description carries the full burden, and it does well by disclosing output behavior (confidence and stable reason code) and an important behavioral limitation (match-context eligibility). It also notes reuse of audit normalize/duplicate rules, adding useful context beyond the schema.

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 compact and front-loaded with the core verb and resource. Every clause contributes useful information: the taxonomy list, the output guarantee, and the eligibility constraint. There is no filler or redundancy.

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?

The description covers the purpose, output, and one eligibility rule, which is adequate for a high-level understanding. However, with no output schema and no annotations, the missing semantics for four control parameters and the lack of any alternative routing to sibling tools leave meaningful gaps for correct invocation.

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 only 33%, and the description partially compensates by explaining invoices (PO/receipt/entity/tax/approval fields) and items (enables inconsistent-tax → tax_review). But key parameters—today, include_audit_tax, include_duplicates, and po_amount_tolerance_pct—are undocumented in both the schema and description, leaving the agent without enough information to set them correctly.

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 names a specific operation—classifying vendor invoices into the AP exception taxonomy—and enumerates the concrete exception categories, so there is no ambiguity about what the tool does. It clearly distinguishes itself from sibling audit or normalization tools by focusing on taxonomy assignment rather than auditing or cleaning.

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 description implies when to use the tool (when AP exceptions need classification) and states an input eligibility constraint (invoices without match-context fields qualify only for duplicate and tax_review). However, it does not explicitly name alternatives like audit_invoices or give when-not-to-use guidance, leaving some selection reasoning to the agent.

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