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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, lowering the bar. The description adds that a JSON report is returned, but it does not say whether an invalid invoice produces an error or a report, nor how findings are surfaced — useful context for a validator that is left unstated.

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 short sentences, front-loaded with the purpose, then accepted formats, then return shape. No filler; minor loss because the return-value sentence is vague ('a JSON report') rather than informative.

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?

A validation tool's key output is the verdict and its findings, and with no output schema the description should sketch the report's contents. It states only that a JSON report exists, leaving the agent unable to anticipate success/failure signaling or result structure.

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 the nested file object, upload_id vs content_base64 alternative, and the 50 MB limit are all already documented in structured fields. The description's 'Accepts pdf, xml' repeats the schema's own wording rather than adding format or encoding guidance. Baseline 3 applies.

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 ('Check') and resource ('XRechnung and ZUGFeRD invoices') plus the standard applied ('official rules'), which clearly separates it from siblings like create-einvoice and extract-einvoice-xml. It stops short of naming those siblings explicitly, so no credit for direct differentiation.

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 gives no when-to-use guidance, no exclusions, and never points to the related create-einvoice, extract-einvoice-xml, or einvoice-to-pdf tools. An agent must infer the workflow position from the tool name alone.

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