rechnungsapi-mcp

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

No annotations exist, so the description carries the full behavioral burden, yet it only offers the vague quality claim 'high-accuracy analyzer.' It does not state that this is a read-only extraction, whether processing is synchronous or may take time, any size/rate limits, or what happens on unparseable input — all relevant for an OCR-style 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?

A single front-loaded sentence with the verb and output first, followed by input formats. No filler, no redundant restatement of the tool name.

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 2-parameter extraction tool with 100% schema coverage this is roughly minimally adequate, but with no output schema the description should say more about the shape of the returned invoice JSON, and with no annotations it should clarify safety and the sync-vs-async choice among its many siblings.

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 both pdfBase64 and withLineItems are already documented in the schema, establishing a baseline of 3. The description adds nothing beyond what the schema provides (it repeats the supported formats already in the pdfBase64 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?

States a specific verb+resource ('Extract structured invoice JSON') and enumerates accepted input formats (PDF/PNG/JPEG/TIFF), so the agent knows exactly what the tool produces and consumes. It does not distinguish itself from the sibling async variants (analyze_pdf_invoice_async_submit/status) or from create_zugferd_from_pdf, so it stays at 4.

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?

No when-to-use or when-not-to-use guidance is given. The description never mentions that synchronous analysis is the alternative to the async submit/status siblings, nor when to prefer a create_zugferd_from_pdf path over plain extraction. Usage is left entirely 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?

No annotations are provided, so the description carries the full behavioral burden. It discloses that the operation is a status poll tied to a prior submission, but says nothing about polling cadence, terminal status values, behavior for an unknown/expired jobId, or retention of results — all material for a polling tool with zero annotation coverage.

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?

One sentence, no filler, and the operative verb is front-loaded with the origin of the jobId as a trailing clause. Nothing could be trimmed without losing routing information.

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?

There is no output schema and no annotations, so the description must explain the return contract — but it never mentions what statuses come back (e.g. pending/running/succeeded/failed) or what the caller should expect next. For a polling tool whose entire value is the returned status, this is a significant incompleteness.

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% and the single jobId parameter is already documented as 'the job_id returned by analyze_pdf_invoice_async_submit.' The description adds no format, validation, or lifecycle detail beyond the schema, so the 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+resource ('Poll the status of an asynchronous PDF invoice analysis job') and ties the resource to the exact sibling that creates it (analyze_pdf_invoice_async_submit). An agent can distinguish this polling tool from the submit tool and from the synchronous analyze_pdf_invoice without opening any 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?

The description implies the usage context by referencing the submit tool, so an agent can infer 'call this after submitting a job.' However it gives no explicit guidance on when to call, how often to poll, or what to do when the job reaches a terminal state.

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 burden and does disclose the asynchronous nature and the job_id return, which is genuinely useful behavioral context. It omits size limits, retention/failure behavior, or auth requirements, so it is adequate but not rich.

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?

Two sentences, zero filler, with the key constraint (too large for sync) and the return/polling contract front-loaded. Every clause earns its place.

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?

No output schema exists, and the description compensates by naming the return value (job_id) and the polling tool, which is the essential missing piece. It stops short of documenting practical limits or failure handling, so a small gap remains.

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 both pdfBase64 and withLineItems are already documented in the schema. The description adds no format, encoding, or size guidance beyond that, so the 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 (submit) and resource (large scanned/PDF invoice) with the operational mode (asynchronous analysis), and explicitly positions it against the sibling analyze_pdf_invoice by scoping to files too large for the synchronous path. An agent can route between the sync and async analyzers without opening the 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?

The parenthetical 'for files too large for the synchronous analyzer' gives the exact selection condition versus the sibling tool, and the description names the follow-up tool (analyze_pdf_invoice_async_status) with the job_id needed to call it. This is explicit when-to-use plus the required next step.

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?

No annotations are provided, so the description carries the full behavioral burden, yet it only restates the transformation. It omits whether auth is required, whether the operation is idempotent, what happens on validation failure, and that the optional transport triggers an email send in the same call.

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?

A single front-loaded sentence with no filler; the core verb and resource lead the line. It is efficient though perhaps too terse given what it needs to convey.

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?

With no output schema and no annotations, a creation tool should say what it returns (the XML string, a file handle, a URL) and how errors surface. The description says nothing about the return value or failure behavior, leaving a real gap for an agent invoking it blind.

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 both parameters are already documented in the schema with references to the EN 16931 business terms and transport options. The description adds nothing beyond what the schema already conveys, matching the baseline 3.

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 (create), resource (XRechnung XML document), and input (structured invoice JSON). The format distinction from the ZUGFeRD siblings is implied by 'XRechnung' and 'XML,' but no sibling is named or contrasted.

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?

There is no guidance on when to use this tool versus create_zugferd_invoice, create_zugferd_pdf, or validate_xrechnung_xml. The agent must infer the choice of e-invoice format and validation workflow on its own.

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 burden, and it does disclose the internal pipeline (analysis, validation, embedding) and that the output is validated PDF/A-3. It does not state what happens on validation failure, whether the call is synchronous or long-running, any input size limits, or how the resulting PDF is returned — all material for a heavy conversion operation.

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?

A single front-loaded sentence with the core action first and the pipeline detail in a parenthetical; no filler. Slightly dense, but every clause earns its place.

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 conversion tool with no output schema and no annotations, the description should say what comes back (base64 payload, file path, download URL?) and how failures surface. It conveys the product but leaves the return contract unstated, which is the main gap an agent needs to plan around.

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 both parameters are already documented (fileName, pdfBase64 with accepted formats). The description adds no syntax, encoding, or size detail beyond the schema, so the 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 and resource: convert a PDF or scanned image invoice into a validated ZUGFeRD PDF/A-3. The input-domain phrase ('from a PDF or scanned image') implicitly separates it from create_zugferd_pdf, but the sibling is never named, so the agent must infer the distinction rather than being told it.

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?

'in one call (analyzes, validates, and embeds in a single step)' implies when this is preferable to the multi-step analyze_* + create_zugferd_pdf path, which is useful implied guidance. However, no alternative is named explicitly and no preconditions (e.g. input must already be an invoice) are 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?

No annotations are provided, so the description carries the full burden. It usefully discloses the output format (PDF/A-3 with embedded XRechnung XML), but says nothing about permissions, failure modes, or the email side effect that the transport parameter triggers. For a creation tool with zero annotation coverage this is adequate but incomplete.

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?

A single tight sentence, front-loaded with the verb and the produced artifact, with parenthetical clarification of the embedded XML. Nothing extraneous.

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?

With no output schema, the description should say what is returned (e.g., generated PDF bytes/base64 or a download reference), and it does not. It also omits the email-delivery behavior when transport is set. Given nested-object inputs and a mutation-style tool, this leaves meaningful gaps.

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 three parameters are already documented in the schema, including the EN 16931 field reference and the email-transport link. The description restates the inputs at a high level without adding syntax or format details beyond the schema, so 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 (Create) and resource (ZUGFeRD PDF/A-3 e-invoice) and clarifies the artifact ('visual PDF with embedded XRechnung XML'), which separates it from create_xrechnung (XML only) and create_zugferd_pdf. It doesn't explicitly name a sibling to route against, so it stops short of a 5.

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?

Input prerequisites are implied ('from structured invoice JSON plus a visual PDF template'), telling the agent it needs both JSON data and a base PDF. However there is no explicit when-to-use guidance or naming of alternatives such as create_zugferd_from_pdf or create_zugferd_pdf, leaving 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?

No annotations are supplied, so the description carries the full behavioral burden, yet it discloses only the transformation itself. It says nothing about the response shape (base64 string vs. file/URL) despite there being no output schema, nor whether the XML is validated before embedding, nor whether the operation is synchronous. The output-schema gap is the most consequential omission.

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?

A single front-loaded sentence that states the operation, its inputs, and its output with no filler or redundancy.

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 two-parameter, fully documented transformation the core is covered, but with no annotations and no output schema the description should at least say what comes back (e.g. a base64 ZUGFeRD PDF). That single missing detail leaves the call contract slightly incomplete.

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% and both parameters are documented in the schema (invoicePdf64 = base64 PDF, xrechnungXml = XML to embed), so baseline 3 applies. The description adds only the qualifier 'existing' and the visual/PDF framing, adding little beyond the structured fields.

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 gives a precise verb (embed), both inputs (an existing XRechnung XML and a visual PDF), and the resulting artifact (a ZUGFeRD PDF). This implicitly separates it from create_zugferd_from_pdf, which starts from a PDF rather than an already-prepared XML, though no sibling is named explicitly.

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?

Usage is only implied by the word 'existing' — an agent can infer this tool is for when an XRechnung XML already exists. There is no explicit when-to-use/when-not statement and no pointer to the alternatives (create_xrechnung, create_zugferd_from_pdf, validate_xrechnung_xml) that a routing agent would need.

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?

No annotations are provided, so the description carries the burden alone. It usefully discloses the return format ('structured JSON'), but says nothing about failure modes such as a PDF lacking an embedded XRechnung or an invalid ZUGFeRD container, nor about side effects or permissions.

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?

A single front-loaded sentence with zero waste; the operation and its output are stated immediately.

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 one-parameter extraction tool with no output schema, the description is adequate but thin: it promises 'structured JSON' without indicating the shape of that JSON, and gives no error-behavior context. It covers the happy path only.

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% and the description adds nothing about the single zugferd64 parameter (base64 encoding is already documented in the schema). Baseline 3 applies when the schema does the heavy lifting.

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?

Specific verb (Extract) plus resource (embedded XRechnung XML) and source (ZUGFeRD PDF), making the operation unambiguous. However, it does not differentiate itself from siblings like analyze_pdf_invoice or validate_zugferd_pdf, which also consume PDFs, so it lands at 4 rather than 5.

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?

No statement of when to choose this tool over the sibling extractors, validators, or analyzers, and no prerequisites or exclusions are given. The use case is only loosely implied by the operation itself.

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 burden. It usefully discloses that validation covers two layers (XSD schema plus business rules), which is more than the name conveys, but says nothing about outcome reporting, error detail, severity levels, or whether a failed document still returns results.

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?

A single front-loaded sentence with no filler; the verb and scope come first and every word earns its place.

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 validator with no annotations and no output schema, the description should at minimum tell the agent what a call returns (pass/fail flag, list of violations, severity) and which XRechnung profile/version is enforced. None of that is present, so an agent cannot anticipate the result.

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?

Only one parameter exists and schema description coverage is 100%, so the schema already documents 'xml' fully. The description adds no format constraints (size limits, encoding, whether the XML can be a file reference vs inline content), which is the baseline for a fully-covered 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?

States a specific verb (validate) and resource (XRechnung XML document) and adds the validation dimensions. It is clearly distinct from the create_/extract_/analyze_ siblings, though it never explicitly contrasts itself with the similar-looking validate_zugferd_pdf, leaving that separation to the resource noun.

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?

There is no when-to-use guidance and no mention of alternatives, despite validate_zugferd_pdf sitting in the sibling list as the obvious near-neighbour. Usage is only inferable from the tool name.

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?

No annotations are provided, so the description carries the full behavioral burden. It narrows validation to the embedded XML (useful scoping), but says nothing about what is checked, whether the PDF/A conformance or visual content is validated, what a failure returns, or whether external services/files are required.

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?

A single tight sentence with the key scope qualifier (embedded XML) front-loaded; no filler. It is arguably under-specified rather than over-long, but structurally clean.

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?

With no annotations and no output schema, the description must explain the validation outcome and error semantics, and it does neither. Given a sibling validate_xrechnung_xml and a family of ZUGFeRD tools, an agent also lacks the differentiation needed to pick correctly.

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%, with both zugferdFile64 and comparePDF2XML documented in the schema, so the baseline is 3. The description adds no meaning beyond the schema, and notably never mentions the comparePDF2XML cross-check option.

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 (validate) and a specific resource (a ZUGFeRD PDF's embedded XML content), which is meaningfully narrower than validating the PDF as a whole. It does not, however, distinguish itself from the sibling validate_xrechnung_xml or explain how it relates to create_zugferd_from_pdf / extract_xrechnung_from_zugferd.

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?

There is no statement of when to reach for this tool versus validate_xrechnung_xml (a sibling validation tool) or the various create/extract siblings. The agent must infer usage purely from the name and the format label.

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