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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds genuinely non-structured context: the service is free with an anonymous daily limit when no API key is present, and files are processed per-request with no document archive (a retention/privacy statement). It does not say what happens on an unsupported format or an unparseable file, which keeps it short of a 5.

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?

Three tight sentences, front-loaded with what is read and what comes back, then the optional HTML, then the commercial/retention caveats. No filler, and each clause carries distinct information an agent would otherwise have to discover by trial.

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?

With no output schema, the description carries the return-value burden and does it well by listing the extracted sections and the optional HTML variant. The remaining gaps are failure behavior (unsupported format, URL refusal) and the requirement to supply exactly one of file_url or file_base64, both of which are handled in the schema rather than the prose.

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 every parameter is already documented in the schema, including the file_url/file_base64 choice and the locale enum. The description only reinforces the html flag ('Optionally returns print-ready HTML') and says nothing additional about locale, filename, or the mutual exclusivity of the two file inputs. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb and resource ('Reads an e-invoice') and enumerates the supported formats (XRechnung, ZUGFeRD, Factur-X, Peppol BIS, UBL, CII) plus exactly what structured output is produced (parties, lines, totals, VAT, payment details). That is enough to tell it apart from check_invoice or convert_invoice in practice, but no sibling is named explicitly, so differentiation is inferred rather than stated.

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?

Usage is implied: call this to extract invoice data from a file, and set html=true if you want a rendered document. There is no explicit 'use this instead of X when Y' routing, and no stated preconditions such as needing a supported format or a reachable URL — the refusal rule for private/local addresses lives only in the schema.

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