Create Purchase Invoice from PDF

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

The description discloses key behavioral traits beyond annotations: it attaches the source file, never recalculates vat_price/gross_price, and auto-derives base_* from currency_rate. Annotations already indicate openWorldHint=true, but the description adds concrete rules for price fields. No contradiction with annotations is present.

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 three sentences, front-loaded with the primary purpose. It efficiently conveys critical contract rules without excess. However, the last phrase 'base_* may lock actual EUR settlement' is slightly ambiguous, and the description could be even more concise without losing clarity.

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 tool with 18 parameters (7 required) and no output schema, the description covers the main behavioral aspects and parameter semantics. It lacks explicit error-handling guidance or mention that file_path must be accessible, but the schema and context signals partially compensate. The sibling list indicates this is a specialized PDF-based creation tool, which is clear.

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?

With 100% schema description coverage, the baseline is 3. The description adds significant value by clarifying special handling for vat_price and gross_price ('never recalculate'), currency_rate ('EUR per 1 foreign unit'), and base_* fields ('auto-derived from currency_rate when omitted'). This goes beyond the schema descriptions which are mostly straightforward labels.

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 defines the tool's action: 'Create a draft purchase invoice from extracted document data and attach the source file.' The verb 'create' and resource 'purchase invoice' are specific, and the source 'from extracted PDF' distinguishes it from other invoice creation tools like 'create_purchase_invoice' or 'extract_pdf_invoice'.

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 provides explicit when-to-use guidance: 'Direct-call contract: pass exact invoice vat_price/gross_price when known, never recalculate; non-EUR requires currency_rate (EUR per 1 foreign unit); base_* may lock actual EUR settlement.' This instructs the agent on correct parameter handling and implies when not to use the tool (e.g., if prices need recalculation).

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