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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is in disclosing the transformation contract: which input standards are accepted and what the normalized output contains. It could say more about failure behavior on non-conforming or non-e-invoice XML, but the core conversion semantics are stated.

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?

Front-loaded with the action and supported standards, then the output shape — good ordering. The trailing 'Pass the XML document as a string' sentence duplicates the schema's `xml` description and could be dropped without loss.

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 correctly enumerates the returned JSON fields (parties, line items, totals, VAT ids, payment details), so an agent knows what it gets back. Input, supported standards, and auth/billing context are all covered between description and schema.

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 coverage is 100%, including a description for `xml` and a detailed note on `api_key` quota behavior, so the schema carries the load. The description's 'pass the XML document as a string' only restates the schema and adds no format or size nuance.

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 (parse) and resource (EN 16931 e-invoice XML) and enumerates the concrete dialects it accepts (CII/Factur-X/ZUGFeRD/XRechnung, UBL/Peppol BIS). This clearly distinguishes it from all create_* siblings, which generate rather than parse documents.

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 makes the trigger condition clear — you have an e-invoice XML document and want normalized JSON. No explicit 'not for X' exclusion or named alternative is given, but no sibling competes for this job (get_document_schema only returns schemas).

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