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

Annotations only supply the generic profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true, destructiveHint=false), while the description adds real operational context: uncertain fields are emitted as 'KORRIGIEREN'/'1900-01-01' placeholders flagged with issue code EXTRACTION_UNCERTAIN, the XML path sets source='xml', and the call requires an active subscription or credit. That is meaningful disclosure beyond the structured fields, and it does not contradict the annotations.

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-loads the action and the correction workflow, and nearly every clause carries new information (placeholders, issue code, XML fallback, billing requirement). It is a dense multi-clause construction rather than a tight set of sentences, which costs a point but not readability of the core intent.

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?

An output schema exists, so return values need no prose, and the description still covers the workflow, the sentinel-value/error semantics, the source-of-truth branch, and the account prerequisite. For a two-parameter extraction tool with annotations and an output schema, nothing an agent needs is missing.

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 upload_id vs pdf_base64, the base64/25 MB constraint, and the mutual exclusivity are already fully documented in the schema. The description reinforces the upload_id reuse across create_zugferd but adds little syntax or format meaning beyond it, so the baseline of 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 precise verb and resource: extraction of EN-16931 invoice data plus validation issues from an uploaded PDF. It also distinguishes itself from sibling create_zugferd by positioning itself as the correction step that precedes it, so an agent can place it in the pipeline without opening another schema.

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?

Gives an explicit ordered workflow: extract, show fields and issues to the user, let them correct, then call create_zugferd with the corrected invoice and the same upload_id. It also defines a condition branch (embedded ZUGFeRD/Factur-X XML vs. LLM reading of the print image), leaving little to inference.

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