Invoice Duplicate Recovery

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

Annotations already mark readOnlyHint=true, openWorldHint=false, idempotentHint=true, destructiveHint=false. The description adds context by confirming it never sends requests and never takes automatic financial action, and it discloses a 0.05 USDC pricing charge on Base. It stops slightly short of detailing the exact output bundle shape, but the non-action boundaries are transparent.

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?

Three sentences: intended computation, explicit non-behaviors, and price. The non-behaviors are front-loaded immediately after the purpose. The pricing sentence is separate and could arguably be moved to annotations, but it is one short sentence and earns its place.

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 could mention what the evidence bundle looks like, but the core invocation semantics and constraints are well covered. The bounded-job pricing is included. The only real gap is a more concrete description of the return value structure, which is partly offset by the clear purpose and non-action boundaries.

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 some burden. It names approved invoices, payments, and recorded credits as the inputs, matching the three parameters. However, it does not add meaning about the 'caller-supplied' format (IDs, currency, amount exactness) beyond what the schema itself already documents in each property.

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 uses a specific verb ('Computes exact overpayments...produces an evidence bundle') and identifies the resource/domain (approved invoices, payments, recorded credits). It clearly distinguishes scope and non-scope, e.g., 'Never sends requests, never asserts legal refund entitlement, and never takes automatic financial action' — no sibling differentiation needed since none exist.

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 clarifies exactly when to use the tool: when computing overpayments and producing evidence for vendor credit review. It explicitly excludes use cases requiring sending requests, asserting legal entitlement, or automatic financial action, so an agent knows not to invoke it for those outcomes.

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