netintel_extract_invoice

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

With no annotations, the description carries the full behavioral burden, and it does disclose two useful traits: the backing model ('using Claude Haiku' — relevant for cost/latency/accuracy expectations) and the return shape (a flat JSON list of fields, valuable since no output schema exists). It does not disclose input constraints (e.g. that only plain text is accepted, not PDFs or images), size limits, or behavior on non-invoice input.

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?

It is a single front-loaded sentence with the purpose first and the return payload after, which is sound ordering. But the description visibly terminates mid-clause with an ellipsis ('expense processing, and…'), leaving an obviously unfinished thought rather than an intentionally concise statement.

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 one-parameter, no-annotation, no-output-schema tool, the description supplies the essentials: what it extracts, what it returns, and which model does the work. An agent can call it correctly from this text. The remaining gap is input eligibility — nothing clarifies whether PDFs, images, or only pre-extracted text are acceptable.

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?

There is one parameter ('text') at 0% schema description coverage, so the schema adds nothing. The phrase 'from invoice or receipt text' implies the input should be raw extracted text rather than a file, URL, or image, which is genuinely useful. Beyond that, format, length limits, and quality expectations for the input are unstated.

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?

States a specific verb and resource — 'Extract structured data from invoice or receipt text' — and enumerates the target fields (vendor, invoice number, dates, line items, subtotal, tax, total, currency). The invoice/receipt domain implicitly separates it from generic siblings like netintel_extract, netintel_extract_table and netintel_extract_resume, but no sibling is ever named. The sentence is also truncated with an ellipsis, so the stated purpose is materially cut off.

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 usage through example scenarios ('automate accounts-payable, expense processing...'), giving an agent a sense of the intended context. However, it names no alternatives and no exclusions: nothing tells the agent to prefer netintel_pdf_parse or netintel_extract_table for PDFs/tables, or netintel_extract_contact for non-financial documents. Usage is only implied, not guided.

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