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

With annotations declaring readOnly and idempotent, the description adds valuable context: requires an API key, costs 1 document, decides syntax from the root element, reports unmodeled content, and refuses PDFs with an explanation. No contradiction with annotations; behavior is fully disclosed beyond what annotations alone indicate.

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?

The description is dense but every sentence contributes: input constraints, accepted formats, error behavior, return values, cost, and limitations. It is slightly long but warranted given the tool's complexity and the need to prevent common misuse (e.g., sending PDF containers). Structure is logical: definition, usage trigger, exclusions, caveats, requirements.

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?

Despite having no output schema, the description enumerates expected return elements (syntax, BT-24/BT-23, teaching errors, unmodeled content) and clarifies edge cases (credit notes accepted, PDFs refused, pre-flight not authoritative). It also mentions API key and cost. This makes the tool's behavior and constraints complete for an agent to decide and invoke appropriately.

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 already covers the 'xml' parameter (complete text, not a path, allowed root elements, not PDF bytes). The tool description goes further by instructing to send the file as-is without pre-determining syntax or document type, explaining why (tool decides from root element), and reinforcing that a PDF should not be sent. This adds operational meaning beyond the schema.

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 clearly states the tool validates an existing e-invoice file (UBL or CII) and returns teaching errors, syntax, BT-24/BT-23, and unmodeled content. It distinguishes itself from sibling validate_invoice by explicitly saying it returns the same errors plus additional file-specific information, making its scope clear.

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?

Provides explicit when-to-use guidance: "Use it when someone says 'this invoice was rejected, why?' and hands you a file." It also gives clear exclusions (XML only, not PDF; extract XML from Factur-X/ZUGFeRD; PDFs are refused and should not be retried) and notes credit notes are accepted. The pre-flight disclaimer (not an authority) further calibrates expectations.

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