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

Annotations already mark readOnlyHint=true, but the description adds meaningful behavioral detail: 'Nothing is stored: the document is parsed in memory and discarded.' It also discloses limitations (not XSD validation, not full EN 16931 Schematron suite) and an important nuance: a file that passes can still be rejected by a portal. This goes well beyond the annotation.

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 long but well-structured and front-loaded with the core purpose. It uses a clear 'What this does NOT do' section and bullet-like lists. Every sentence carries useful information, though the detailed enumeration of checked rules (BT-10, BT-34, etc.) could be considered verbose for an AI agent. Still, it is appropriately sized for a complex validation tool.

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?

For a tool that validates complex e-invoices, the description is remarkably complete. It covers accepted input formats, the specific rules checked, limitations and exclusions, behavioral side effects (memory-only, no storage), and what the output will contain ('reports the syntax and profile it found along with the invoice's key fields'). No gaps remain that would prevent correct selection and invocation.

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% and the single 'xml' parameter is well described. The description adds substantial meaning: it accepts XRechnung and ZUGFeRD XML in EN 16931 syntax (CII and UBL), clarifies the input must be the extracted XML not the PDF, and explains what the tool does with that XML. This goes far beyond the schema's basic description.

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 existing electronic invoice and reports what is wrong with it.' It also clarifies it identifies syntax/profile and key fields, answering 'what is this file?'. This clearly differentiates it from siblings like create_xrechnung and check_leitweg_id, and the 'What this does NOT do' section further distinguishes it from the official KoSIT Prüftool.

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-not: it is not the KoSIT Prüftool, does not check XSD schema, and reads XML only (not ZUGFeRD PDFs). It also states a passing file may still be rejected by a Rechnungseingangsportal. However, it does not explicitly mention sibling tools like check_leitweg_id when the task is only a Leitweg-ID check, so it lacks direct alternative routing.

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