ZUGFeRD Validator

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

With no annotations, the description must carry the burden of behavioral disclosure. It only states what the tool checks, but does not mention whether it is read-only, what happens on mismatch, or what the return value/response looks like. This lack of behavioral detail is a significant gap.

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 a single, clear sentence that conveys the core purpose without any unnecessary words. It is front-loaded with the verb and resource, making it immediately understandable.

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?

While the tool is simple (one parameter, no output schema), the description omits what the result of the check is (e.g., boolean, error message). Without an output schema, the description should clarify the return behavior, which is critical for an agent to know how to handle the response. This incompleteness leaves a significant gap.

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?

The single parameter 'pdf_content' is well-described in the schema (base64-encoded ZUGFeRD PDF content), providing 100% coverage. The description itself adds no additional parameter meaning, but the schema is sufficient, so baseline 3 is appropriate.

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 a specific action ('Prüft' - checks) and a specific resource/scope (whether visible PDF data matches embedded XML data). It also distinguishes itself from siblings like create_invoice and validate_invoice by focusing on consistency between two data representations.

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 implies its usage for verifying consistency but offers no explicit guidance on when to use it versus alternatives like validate_invoice or extract_xml. It does not mention prerequisites or exclusions, so the usage context is inferred rather than stated.

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

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

With no annotations, the description carries the full load and does add real behavioral context: base64 attachments inflate both request and response, only small attachments should be sent here, and with attachments the ZUGFeRD response contains only pdf_base64 with the XML embedded in the PDF. It also states 'Wir speichern nichts', disclosing statelessness. It omits permission/tier constraints and the response shape for the no-attachment case, which the schema only partly implies.

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?

Five sentences, front-loaded with what is produced and in which formats, followed by capability scope, then the attachment caveats. Every sentence adds information; nothing is redundant with the schema.

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 25-parameter mutation tool with no output schema, the description supplies the essential behavioral facts: output format choice, response composition with attachments, size limits, and that nothing is persisted. A minor gap is that the return payload for the plain (no-attachment) case is only implied, not stated.

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 schema already documents all 25 parameters in detail. The description adds only marginal parameter meaning — the feature list (line items, pass-through items, allowances/charges, billing period, prepaid amounts, tax number, SEPA direct debit, attachments) maps loosely to parameters and the attachment size caveat is useful, but no new syntax or format semantics 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 opens with a specific verb and artifact: it creates a valid e-invoice from structured data, and immediately names the two concrete output formats (ZUGFeRD PDF/A-3 with embedded XML, or XRechnung XML). It is clearly distinguishable from siblings such as validate_invoice or validation_report because it is the only tool that produces an invoice rather than checking one.

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?

It establishes the input context (structured data) and the format decision, and explicitly routes the agent to extract_xml when the XML is needed from a ZUGFeRD PDF with attachments. It does not explicitly say when to prefer validate_invoice or check_consistency instead, though the self_check parameter covers the in-line validation case.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates the operation is a read-only extraction, but it does not disclose potential errors (e.g., missing XML), output format, or any side effects beyond what the purpose already states.

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 a single, front-loaded sentence with no wasted words or redundant information. It is concise and to the point.

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?

Given the tool's simplicity (one parameter, no annotations, no output schema), the description plus schema provide adequate context for basic usage. However, the lack of output format specification and error handling details leaves minor gaps, but not enough to reduce to a 'minimum viable' score.

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?

The schema fully describes the sole parameter pdf_content as 'Base64-kodierter Inhalt der ZUGFeRD-PDF-Datei', providing 100% coverage. The description does not add any additional parameter meaning beyond the schema, 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?

The description uses a specific verb ('Extrahiert' = extracts) and clearly specifies the resource (embedded XML from a ZUGFeRD/Factur-X PDF). It inherently distinguishes from sibling tools like check_consistency, create_invoice, and validate_invoice, which serve different purposes.

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 implies usage (extracting XML from a PDF) but provides no explicit guidance on when to use this tool versus alternatives. It does not mention exclusions or name sibling tools as alternatives, leaving usage context only implied.

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

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It states the tool validates against EN 16931 and returns structured results with correction suggestions, conveying the core behavior and output format. It does not mention side effects, but none are expected for a validation tool.

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 a single, concise sentence that is front-loaded with the action and resource, and includes important details. No unnecessary words.

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?

Given the tool's complexity (3 parameters, no output schema), the description provides adequate context: input types, validation standard, and output nature. It does not detail the result structure, but 'structured results with correction suggestions' gives a sufficient high-level picture for an agent to select and invoke the tool.

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?

All parameters are fully described in the schema (100% coverage), so the description does not need to add parameter-level details. It does mention file types and standards which relate to parameters, but this does not go 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 e-invoices (ZUGFeRD/Factur-X PDF or XRechnung XML) against EN 16931 and returns structured results with correction suggestions. It uses a specific verb ('Validiert') and a distinct resource, differentiating it from siblings like 'check_consistency' and 'extract_xml'.

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 explains the tool is for validating e-invoices against a specific standard, giving clear context for when to use it. It does not explicitly exclude alternatives or mention when not to use it, but the context is sufficient for distinguishing it from sibling tools.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the return encoding (base64 PDF), optional attachment behavior, the exact content of the report, and even a tariff restriction. It does not explicitly state absence of side effects, but for a report-generation tool the disclosed details are strong.

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 and well-structured: it opens with the core purpose, then lists report contents, optional attachment, return format, and tariff requirement. Every sentence carries useful information with no filler or repetition.

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?

Without an output schema or annotations, the description compensates well by detailing report contents, output encoding, and optional attachment. It does not mention error conditions or prerequisites beyond the tariff note, but for a PDF-generation tool the description is largely sufficient.

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 all five parameters already have descriptions and enums. The tool description reinforces attach_source and file_type semantics but adds no new parameter-level information beyond what the schema provides, meeting the baseline.

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 states a specific verb and resource: it generates a validation report as a PDF/A-3b from an e-invoice. It also names concrete report contents and the base64 return format. However, it does not explicitly distinguish itself from the sibling tool validate_invoice, so the differentiation is only implicit.

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 provides clear context ('zum Ablegen und Weitergeben' and 'auf Wunsch wird die Rechnung angehängt') implying this tool is for producing an archival report after validation. But it gives no explicit when-to-use vs. alternatives such as validate_invoice or check_consistency, leaving the selection to inference.

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

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

With no annotations at all, the description carries the full burden and does so well: it discloses that the HTML is sanitized (no scripts, no external resource loading), that attachments come back separately, that it does not consume the validation quota but has its own daily limit, and that nothing is persisted. These are exactly the behavioral facts an agent cannot infer from the schema.

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 core purpose in the first clause and then adds one sentence per distinct fact (return shape, sanitization, check flag, quota, no storage), so every sentence earns its place. Slightly dense with stacked parentheticals, which slows parsing marginally but adds no filler.

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 four-parameter tool with no output schema and no annotations, the description covers what the tool returns (HTML plus separated attachments), how output is constrained (sanitized rendering), side effects (nothing stored) and cost (own daily limit, no quota consumption). Nothing an agent needs before calling it 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 the baseline is 3, but the description adds real meaning on top: it explains what check=true actually yields (a short validation summary) and ties file_type values to concrete formats (pdf for ZUGFeRD/Factur-X, xml for XRechnung/CII). Only the language parameter's effect on the rendered output is left to 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?

Names a specific verb ('zeigt ... an') and resource (E-Rechnung) and enumerates the accepted formats (XRechnung/CII-XML, ZUGFeRD/Factur-X-PDF) plus the return artifacts (HTML rendering and separate attachments). This is clearly a render/view operation, which distinguishes it from validate_invoice, check_consistency and extract_xml in the sibling list.

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 a conditional usage hint for one parameter ('Mit check=true kommt die Kurzfassung der Prüfung dazu'), which tells the agent when to opt into validation output. However, it never states when to choose this tool over validate_invoice or extract_xml, nor which input types are out of scope, so the routing guidance is implied rather than explicit.

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