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

With no annotations provided, the description carries the full burden and does so thoroughly: it discloses file creation with 0700 permissions, refusal inside cache/data roots, cloud-sync warnings, CSV column order, decimal/comma separators, absence of certain fields, exact KSeF amounts, and where paths and sums are reported. This is exceptionally transparent about side effects and output format.

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?

Although the description is long, every paragraph earns its place by covering a distinct concern: purpose, period semantics, directory behavior, CSV contents, and formatting rules. The primary purpose is front-loaded, and there is no redundant or filler text.

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 with two parameters, no annotations, and an output schema, the description is remarkably complete. It explains return-relevant details (paths and sums in the answer), file structure, edge cases for missing archive bodies, and constraints on the working directory. There is no meaningful gap an agent would need filled to invoke it 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 0%, so the description must fully explain both parameters. It does: `period` is defined as a YYYY-MM calendar month with a caching rationale, and `working_directory` is explained as a one-call override with creation, refusal, and warning behaviors. This far exceeds what the bare schema provides.

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 first sentence states a specific verb, resource, and deliverable: 'Write one month of purchase invoices as a CSV an accountant can forward.' This clearly distinguishes the tool from siblings like render_invoice_pdf or list_recent_invoices, which address different outputs and workflows.

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 clear context on when this tool is appropriate: it exports a closed calendar month and can reuse disk-stored results instead of consuming metadata queries. It does not explicitly name sibling tools as alternatives or state when not to use it, but the usage context is unambiguous.

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 behavioral burden and does so thoroughly: it discloses read-only semantics, absence of confirmation flow, a 50-invoice cap with aggregated fallback, the empty-window self-describing response, and the exclusion of personal data. These are non-obvious, agent-relevant behaviors that go far beyond a bare action statement.

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 opening sentence is a model of front-loaded clarity, but the remaining paragraphs are dense and stylized, with narrative explanations that could be tightened. Every sentence carries meaningful behavioral information, so nothing is wasted, but the overall length is greater than necessary for the simplicity of the 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?

Given zero parameters, a rich output schema, and no annotations, the description still covers all critical agent-facing edge cases: the 50-row limit, aggregated totals, empty results, read-only guarantee, and privacy constraints. It leaves no meaningful ambiguity about how the tool behaves in unusual circumstances.

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 tool has zero parameters and the schema covers this fully. The description goes further by explaining why there are no arguments—the caller-driven window would consume the metadata allowance—which gives an agent semantic understanding of the parameter absence and prevents attempts to pass unsupported arguments.

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 first sentence states a specific verb ('List'), a concrete resource ('invoice metadata'), a clear time window ('the last thirty days'), and a grouping ('per subject type'). This immediately distinguishes it from siblings like render_invoice_pdf or export_period_statement, and the later reference to synchronise_invoices further separates its read-only, metadata-focused role.

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 why the tool takes no arguments, mentions the metadata allowance, and notes it is read-only, which implies safe usage. However, it never explicitly states when to choose this tool over alternatives such as synchronise_invoices or review_new_invoices, nor does it name exclusions or conditions that would route an agent to a different sibling.

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?

There are no annotations, so the description carries the entire burden and meets it: no-network/no-quota behavior, vendored official generator, Node requirement with a precise failure mode, working-directory permission and warning rules, production-only verification URL, and untested FA schema variants are all disclosed.

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 front-loaded with a one-sentence purpose and then moves through quota, fidelity, directory behavior, output surface, runtime, and schema compatibility. Each paragraph adds a distinct piece of operational knowledge, and there is 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 tool with no annotations and a bare input schema, the description covers prerequisites, failure modes, supported schema variants, directory semantics, and output-surface differences. An agent has everything needed to decide whether and how to call it.

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?

With 0% schema description coverage, the description fully compensates: ksef_number is explained as the archived-invoice identifier and 'refused' when unsynchronised, and working_directory's override semantics, 0700 creation, refusal locations, and warning conditions are all spelled out.

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 first sentence names a specific action and target: 'Write one archived invoice as the PDF the Ministry's own application shows.' It also distinguishes the tool from the period-statement, listing, and synchronisation siblings by limiting scope to a single archived invoice and stressing that nothing is fetched.

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 clearly situates the tool: use it for one already-synchronised invoice when an official local PDF is needed without spending metadata quota or requiring network. It stops short of explicitly naming sibling tools as alternatives or listing when-not-to-use cases, so a fully explicit routing statement is missing.

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 so thoroughly. It discloses persistence across restarts, the distinction between KSeF acceptance date and seller's issue date, the 20-requests-per-hour budget, the recording of shown invoices, the threshold-drop behavior, and the meaning of marked_as_reviewed. It also notes that personal data from FA(2)/FA(3) bodies never enters the answer.

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 purpose is front-loaded in the first sentence, and the following paragraphs are organized thematically. It is longer than strictly necessary, but each paragraph conveys meaningful nuance about timing, persistence, and tax-period interpretation, so the length 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?

Despite having no annotations and no parameters, the description is complete enough for an agent to invoke the tool correctly and interpret its result. It explains what is recorded, what happens on repeat calls, what marked_as_reviewed indicates, and what data is excluded, while the output schema can carry structured return details.

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 tool has zero parameters and the input schema has no properties, so the baseline is 4. There are no parameters to clarify; the description does add useful context about the implicit per-subject and per-environment comparison, even though no arguments are needed.

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 first sentence states a specific verb and resource: 'Report the invoices that have arrived since a person was last shown any.' This clearly distinguishes the tool from a plain list of invoices and from sibling tools like list_recent_invoices by making the 'new since last viewed' criterion explicit.

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 clearly explains when this tool is appropriate: when the user needs what is new since the last look, which the free Ministry application cannot answer. It also gives operational context such as the 90-day window, the on-disk ledger, and the metadata query budget. It stops short of explicitly naming sibling alternatives and stating 'use X instead,' so it misses a 5.

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 disclosure burden; it does indicate the tool is a read-only reporting operation that returns name and version. It does not state whether any authentication or connector state is required, nor does it warn about failure modes. Adequate but thin for an unannotated 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 no filler or repetition. Every word contributes to identifying the tool's output.

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 parameters, no annotations, and an output schema that already documents the return shape, the description only needs to identify the operation. It does so clearly; extra detail such as auth or connector-state prerequisites would make it fully complete but is not strictly required here.

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 tool takes zero parameters, so there are no parameter semantics to document; the baseline for a parameterless tool applies. The input schema is a bare empty object, consistent with the 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 gives a specific verb ('Report') and a precisely scoped resource ('the name and version of the running KSeF connector'). There are no sibling tools to disambiguate against, and the statement leaves no ambiguity about what the call returns.

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 explicit when-to-use or when-not-to-use guidance is given, and no alternatives are named (none exist among the siblings). For a zero-argument informational tool the intended use is strongly implied, but nothing is stated outright.

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, and it delivers: idempotent retry behavior, continuation of incomplete packages, already_held handling, refusal to return invoice content for data-protection reasons, session_ceilings semantics, and stderr correlation for failure tracing. This is far beyond the minimum expected.

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?

Although the description is long for a zero-parameter tool, every paragraph earns its place: purpose, argument rationale, idempotency, privacy, output fields, and failure correlation. It is front-loaded with the core action and uses backticked field names to structure operational details clearly.

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?

The description is complete for a complex, sensitive synchronisation tool. It explains output fields such as session_ceilings, assumed, already_held, and correlation, while the output schema covers return structure. There is no missing behavioral or safety information that an agent would need to invoke it correctly and safely.

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 has zero properties, so the baseline is 4, but the description adds real meaning by explaining why no arguments are accepted and what would happen if an agent tried to drive the process manually. It turns an empty schema into an intentional design constraint.

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 precise verb phrase: 'Fetch, decrypt and archive every invoice package KSeF finished since the last run.' This names the resource, the action, and the boundary of the operation. It also clarifies the deliberate lack of arguments, which sharply distinguishes it from sibling tools like list_recent_invoices and export_period_statement.

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 clear contextual guidance: this tool runs a KSeF-driven synchronisation since the last run, takes no caller-controlled parameters, and is safe to call again. It does not explicitly name sibling alternatives or state 'use X instead', but the usage context is strong enough for an agent to select it appropriately.

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