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

With no annotations to lean on, the description carries the full burden and does so thoroughly: file is not stored, 5 parses per email per day, email address required and reused for occasional updates, and a prompt-injection guard noting extracted values are data, not instructions. It also discloses the internal consistency checks performed on line items, subtotal, and tax.

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 front-loaded with the core action and the extracted fields, then layers constraints, validation behavior, and privacy/rate-limit terms in descending order of importance. Every sentence conveys a distinct operational fact with no filler, and the consent-style disclosure about email usage justifies its own sentence.

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?

Though no output schema exists, the description effectively documents the return shape by listing extracted fields and the arithmetic cross-checks. Combined with input constraints, rate limits, and storage behavior, an agent has everything needed to call it correctly.

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 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: file_url must be publicly reachable without a login (with a Google Drive sharing example) and email drives the rate limit. Name and company remain undocumented beyond the schema's own descriptions.

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 names a specific verb and resource — extract structured data from an invoice — and enumerates exactly what is extracted (invoice number, dates, PO number, vendor, currency, terms, subtotal, tax, total, line items). This cleanly differentiates it from the sibling parse_purchase_order, which targets a different document type.

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?

Constraints on the input (public https URL, direct download with no login, formats, 10MB limit) are stated, which implies when the tool is usable. However, there is no explicit guidance on when to choose this over siblings like match_po_to_invoice or calculate_invoice_due_date, nor any stated alternatives.

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