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

The description directly contradicts the openWorldHint annotation: it says 'no external research or outbound actions' while the annotation indicates the tool may access the open world. It also does not explain the destructiveHint=true annotation beyond mentioning payment authorization, and the 'Returns a draft' phrase does not address potential destructive side effects.

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 concise and front-loaded with the core purpose, followed by boundary conditions, output type, and pricing/authorization. There is minor redundancy between 'buyer-supplied information only' and 'no external research', but overall each clause contributes useful information without padding.

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 paid tool with five parameters, nested input, no output schema, and non-trivial annotations, the description is incomplete. It does not explain parameter semantics, the exact structure of the returned draft, or how the payment_signature and result_signature work. The contradiction with openWorldHint also undermines an agent's ability to reason about side effects.

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%, and the description adds no meaningful explanation for the five parameters. It only hints that the input is 'supplied text', which loosely maps to source_text, but it does not explain the required brief, audience, result_expires, idempotency_key, result_signature, or payment_signature.

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: 'Extract invoice fields from supplied text', and adds detail on preserving currency and identifiers and marking missing values. It explicitly excludes OCR and accounting posting, which differentiates it from related extraction tools like receipt_text_extraction and entity_extraction.

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 gives useful boundary conditions: it operates only on supplied text, not OCR, and does not post to accounting. It also clarifies that it uses only buyer-supplied information and returns a draft for human review. However, it does not explicitly name sibling alternatives or state when to prefer this over receipt_text_extraction, so it stops short of full routing guidance.

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