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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only lists extracted fields and provides no details about output format, error handling, reliance on OCR, or behavior with invalid/malformed PDFs. This is a significant transparency gap.

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 a single, front-loaded sentence with a clear action phrase and a concise list of fields. It is appropriately sized with no wasted words, though it is somewhat terse given the tool's potential complexity.

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 tool lacks both annotations and an output schema, so the description must explain return behavior. The field list gives some idea of output content, but there is no indication of the output structure (e.g., JSON format), processing limitations, or what happens on failure. The description is insufficient for an agent to fully anticipate tool behavior.

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 input schema already describes both parameters (pdf_path and pdf_base64) with 100% coverage, so the baseline for parameter semantics is met. The description adds no extra information about how these parameters are used, but since the schema is complete, no further compensation is required.

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 performs 'Smart field extraction from invoice' and enumerates the specific fields extracted (invoice number, date, total, VAT, etc.), giving a specific verb+resource. However, it does not distinguish itself from sibling tools like invoice_ocr or invoice_parse_text, so it loses a point for lack of differentiation.

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?

There is no guidance on when to use this tool versus alternatives such as invoice_ocr, invoice_parse_text, or invoice_from_url. No prerequisites, input limitations, or exclusions are mentioned, so the agent is left without usage context.

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