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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered by structured data. The description adds the check categories and the endpoint path, but says nothing about failure behavior, what a failing validation produces, or any rate/permission constraints.

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?

Two tight clauses, front-loaded with the tool's identity and followed immediately by the enumerated checks. The trailing parenthetical endpoint is the only mildly extraneous element, though it is compact and potentially useful.

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?

There is no output schema, so the description carries the burden of explaining the return shape (pass/fail, list of errors, severity) and it does not — it also omits the expected structure of the required 'invoice' object. For a validator whose entire value is the result it returns, this is a meaningful gap.

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 nominally 100%, so the baseline is 3, but the schema's own parameter descriptions are vacuous placeholders ('Structured object parameter invoice'), and the description adds nothing about what the nested invoice object must contain or what toggling check_en16931 actually changes. For a nested-object parameter, this leaves real semantic weight unaddressed.

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 ('Audit') and resource ('extracted invoices') and enumerates the concrete checks performed: line-item math errors, VAT mismatches, and Peppol compliance. It is clear what the tool does, though it never contrasts itself with the similarly-named sibling 'tinplate_peppol_ubl_invoice', so an agent must infer the boundary between validating an invoice and building one.

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 only implied by the phrase 'Audit extracted invoices' — it suggests calling this after invoice extraction, but there is no explicit when-to-use, when-not-to-use, prerequisite (e.g. invoice must already be parsed/structured), or routing to an alternative. An agent gets the general context but no decision rule.

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