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

Beyond the annotations (read-only, idempotent), the description discloses important behaviors: arithmetic validation (net+tax=gross), independent batch total checking, flagging of misread rows with exact differences, and deliberate omission of batch totals for mixed currencies. It also explains CSV encoding for Excel compatibility. No contradictions with annotations.

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, front-loaded with purpose, and every sentence adds value: purpose, validation details, edge-case handling, and output format. No fluff or repetition of schema/annotations.

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?

Given a single parameter, high schema coverage, and the presence of an output schema, the description fully covers input format, validation logic, edge cases, and output encoding. It provides enough context for an agent to select and invoke the tool correctly without needing additional information.

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?

The schema already provides full coverage for the 'urls' parameter. The description adds meaning by specifying accepted input types (PDF or page images) and reinforcing the 20-item limit, which goes slightly beyond the schema but is not redundant.

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 clearly states the tool's function: take up to 20 invoice URLs and return a ledger-ready table with specific fields (number, date, seller, buyer, net/tax/gross, currency). This distinguishes it from siblings like extract_statement or extract_tables, which target different document types.

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 the use case (invoice extraction) and provides constraints (up to 20 URLs, PDF or page images, mixed-currency behavior). It does not explicitly name alternative tools or state when not to use it, but the context is clear enough for an agent to decide.

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