Server Quality Checklist

Tool Scores

• get_organization_krs_chapterB
  3.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It does disclose the Premium+ plan requirement, which is a meaningful access behavior, but it does not mention other behaviors such as historical entry_number handling, error conditions, or what the returned chapter data includes beyond what the schema states.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is extremely compact: two sentences, front-loaded with the primary purpose, followed by the essential plan restriction. Every sentence earns its place and nothing is redundant.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The core invocation is sufficiently defined, and the output schema covers return-value expectations. However, the lack of any relationship to sibling KRS tools leaves an agent uncertain about how this chapter-specific fetch fits with the full-extract and entry-list operations, which is a real gap given those siblings exist.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema already documents the 'chapter' and 'entry_number' parameters in detail, covering about 67% of properties. The description adds the Premium+ condition but does not clarify the 'id' parameter beyond implying it refers to an organization, so it provides only modest value beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Get') and resource ('one KRS chapter') and enumerates the available chapters, making the core purpose clear. It does not explicitly contrast itself with sibling tools like get_organization_krs_extract, so it falls just short of full differentiation.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No guidance is given about when to use this tool versus alternatives such as get_organization_krs_extract or list_organization_krs_entries. The Premium+ note is a restriction, not a usage strategy.

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

• list_organization_krs_entriesB
  3.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It communicates read-only listing behavior and the 'all' scope, which is the core behavioral trait. However, it does not mention pagination, ordering, data currency, or whether the response could be partial or truncated. For a simple list operation with an output schema, this is adequate but not thorough.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is one concise sentence that front-loads the action and scope. Every word earns its place, and there is no redundant information or filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has a simple single-parameter schema and an output schema, so the description does not need to explain return values. However, the presence of related sibling tools with similar KRS terminology means the description could do more to clarify when this tool is preferred over get_organization_krs_extract or get_organization_krs_chapter. It is minimally complete for a straightforward listing tool but leaves some contextual ambiguity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema has one required string parameter 'id' with 0% description coverage. The description says 'for an organization,' which implies 'id' identifies the organization. This adds some meaning beyond the bare schema, but it does not explicitly state whether the id is an organization ID, a KRS number, or some other identifier, so the agent must rely on convention and the tool name.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific action ('List all') and a clear resource ('KRS entries (wpisy) recorded for an organization'). It also clarifies the Polish term, which helps an agent understand the domain. It does not explicitly contrast with sibling tools like get_organization_krs_extract or get_organization_krs_chapter, but the resource scope is reasonably distinct.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies this is the tool to use when all KRS entries for an organization are needed, but it gives no explicit when-to-use guidance and does not mention any alternatives or exclusions. The sibling tools include related KRS operations, so some usage direction would add significant value.

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

• search_organizationsA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. The verb 'Search' implies a read-only operation, and the enumerated dimensions convey what can be filtered, but the description adds no behavioral context beyond that — no mention of how filters combine, result limits, or pagination behavior. Adequate but with clear gaps.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single tightly packed sentence with zero waste. The verb and resource are front-loaded, followed by an efficient enumeration of search dimensions. Every word earns its place, and the sentence is appropriately sized for the tool's scope.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 28 optional parameters, no annotations, and rich filter semantics (TERC codes, address types, status flags, sort behavior), a one-line description is thin. The output schema covers return values, but the description does not disclose how multiple filters interact, whether an empty query returns the entire register, or any caveats about the search. This is a clear completeness gap for such a complex tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema fully documents all 28 parameters with defaults and formats; the baseline of 3 applies. The description adds marginal organizational value by grouping parameters into semantic categories (registry numbers, PKD codes, status flags, address), but it does not explain any parameter semantics beyond what the schema already provides.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Search'), names a precise resource (organizations in the Polish National Court Register), and enumerates concrete search dimensions (name, registry numbers, legal form, PKD codes, status flags, address, pagination). It is immediately distinguishable from its siblings, which are all 'get_*' lookups by exact identifier.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The usage context is implied: this is clearly the criteria-based search tool among siblings that fetch specific organizations or persons by ID. However, the description never explicitly states when to prefer this tool over get_organization (e.g., 'use this when you don't know the KRS number'), nor does it name any alternative or exclusion condition.

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

• get_personA
  3.8/5.0
  Behavior3/5

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

  Annotations are absent, so the description carries the burden. 'Current data' usefully signals a live/current snapshot rather than historical information, and 'Get' implies read-only behavior; however it does not disclose edge-case behavior or authorization expectations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  One focused sentence that front-loads the operation and resource, then identifies the keying parameter. No filler or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a single-parameter read tool with an output schema present, the description supplies the essential selection context. The main omission is routing to sibling get_person_relations, but that gap is already reflected under usage_guidelines.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  With 0% schema description coverage, the description compensates by clarifying that the lone integer 'id' is the KRS person id, not a generic identifier. It does not explain how to obtain the id, but for a single required parameter this is a meaningful semantic addition.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  States a specific action ('Get current data') on a specific resource ('a person appearing in the KRS') keyed by person id. This distinguishes it from sibling get_person_relations, which addresses relationships rather than base person data.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  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 provided. The description implies the tool is for retrieving current person data by id, but does not mention alternatives or exclusions, leaving the agent to infer selection.

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

• get_person_relationsA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description relies on its own wording. It discloses the current-vs-historical scope and names the KRS as the source, which adds context, but it omits details about side effects, authentication needs, or data freshness. The read-only nature is at least implied by 'Get'.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single, front-loaded sentence with no filler. Every part of the description carries meaning and the core scope is presented first.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple two-parameter read operation with an output schema available, the description plus schema covers the essential call semantics. It is slightly incomplete in not offering any routing guidance or caveats about historical relation semantics, but the tool is small enough that this is not a major gap.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema documents 'status' but leaves 'id' undescribed. The description's phrase 'a person's ... relations' clarifies that the 'id' parameter identifies a person, compensating for the schema coverage gap. The status parameter behavior is already covered in the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action ('Get'), the resource ('a person's current or historical relations with organizations'), and the data source ('recorded in the KRS'). It distinguishes this tool from organization-oriented siblings like get_organization_relations, making selection straightforward.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  There is no explicit guidance about when to use this tool versus alternatives such as get_organization_relations. The intended context is implied by the resource wording, but no exclusions or routing hints are provided.

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

• get_organizationA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. It indicates a read operation ('Get') but does not mention limitations, error behavior, authentication, or the distinction between basic data and richer endpoints. The example format for the id (including the 'nip' prefix) is a helpful behavioral clue beyond 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, front-loaded sentence with an inline example. Every word earns its place: it states the action, resource, identifier formats, and examples without any fluff or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple with one parameter and an output schema, so the description does not need to explain return values. The id format is explained clearly, and 'basic data' signals the scope. Minor gap: it does not mention any preconditions or alternatives, but overall it provides sufficient context for correct invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema provides only a bare string parameter with no description (0% coverage). The description fully compensates by explaining that 'id' accepts either a KRS number or a NIP, with illustrative examples ('12345' or 'nip1234567890'). This gives an agent the exact format needed to invoke the tool correctly.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific verb ('Get') and resource ('basic data for an organization'), and identifies the key identifiers (KRS number or NIP). It is distinguishable from sibling tools like search_organizations (search vs get) and get_organization_krs_extract (basic vs extract), though it does not explicitly name them.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage when you have a KRS number or NIP and need basic organization data, but it does not provide explicit when-to-use or when-not-to-use guidance. No alternatives are mentioned, such as using search_organizations when an identifier is unavailable.

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

• list_organization_financial_documentsA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden of behavioral disclosure. It does add useful context: the operation is a read-only listing, and Premium+ access is required. However, it does not mention pagination, period formatting, or error conditions, and with zero annotation coverage some behavioral transparency is still missing.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, efficient sentence with no filler. The action, object, scope, and access requirement are all packed in without redundancy, and the most important information is front-loaded.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple with only one parameter and has an output schema, so the return structure does not need to be described. The description covers what is listed and the plan requirement, and the parameter meaning is reasonably inferable. It lacks an explicit alternative pointer and detailed id format, but those are secondary for such a simple list tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema only defines an unannotated 'id' string, and schema description coverage is 0%. The phrase 'for an organization' gives the key semantic cue that id is the organization identifier, which is helpful. However, it does not specify whether the id is the KRS number, an internal ID, or how to obtain it, leaving some ambiguity.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action ('List') and the resource ('financial document groups by accounting period') plus the data source ('KRS') and scope ('for an organization'). This clearly distinguishes it from the sibling get_organization_financial_document, which fetches a single document rather than listing groups.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives useful context: the tool enumerates document groups and requires a Premium+ plan, which helps an agent decide when it is applicable. It does not explicitly name alternatives or say 'use get_organization_financial_document for a specific document,' but the plural 'groups' strongly implies the enumeration role.

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

• get_organization_beneficial_ownersA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral disclosure burden. It usefully states that the operation requires a Premium+ plan and is keyed by KRS number or NIP. However, it does not mention potential failure modes, whether the operation is read-only, or any response-related behavior beyond what the output schema likely covers.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, front-loaded sentence. It states the purpose first, then the identifier semantics, then the plan requirement. No words are wasted.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple single-parameter lookup with an output schema, the description covers the essentials: what data is returned, how the organization is identified, and the access requirement. It could add format examples for KRS/NIP, but nothing critical is missing for an agent to invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 0%, so the schema provides no meaning for the 'id' parameter. The description compensates by explaining that the id can be a KRS number or NIP, giving the parameter actual semantic meaning. It stops short of specifying exact formats or examples, but for a single-parameter tool this is reasonable.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb-resource pair: 'get the beneficial owners (CRBR) of an organization'. It clearly distinguishes this tool from sibling tools like get_organization or get_organization_relations by identifying the exact data it returns.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives clear context for when to use the tool — when beneficial owners for an organization are needed — and adds the Premium+ plan requirement. It does not explicitly mention alternatives or exclusions, but the use case is unambiguous enough to route selection.

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

• get_organization_relationsA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of conveying behavior. 'Get' clearly signals a read-only operation, and 'current or historical' discloses that the tool can return relation state at different time perspectives. It does not discuss auth or pagination, but for a simple read tool with an output schema, the behavioral disclosure is adequate.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, front-loaded sentence with no filler. It immediately names the resource and the key temporal distinction, and every word contributes to understanding the tool's purpose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is a simple two-parameter read operation and has an output schema, so the description does not need to explain return values. It covers the key scope, entity types, and temporal modes. The only minor gap is the lack of explicit guidance on sibling tool selection, which is already captured in the usage dimension.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema only describes the 'status' parameter, leaving 'id' undocumented. The description compensates by identifying the organization as the entity the id refers to, and by restating the current/historical semantics of status. This gives enough meaning for an agent to understand both parameters despite only 50% schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Get') with a clear resource ('an organization's current or historical relations') and names the entity types involved ('other organizations and people in the KRS'). This clearly distinguishes it from related siblings such as get_organization (entity details) and get_person_relations (person-centric relations).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the tool should be used when retrieving an organization's relation data, and the 'current or historical' wording gives some context for choosing a status. However, it does not explicitly state when to prefer this over alternatives like get_person_relations or get_organization, nor does it provide exclusion criteria.

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

• get_account_balanceA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description bears the full burden of behavioral disclosure. It clearly states the operation is non-consuming ('does not consume account balance') and identifies the result as the current balance in PLN. For a zero-parameter read-only tool, this is sufficient behavioral transparency despite not covering details like authentication or failure modes.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The entire description is one compact, front-loaded sentence with no filler. It states the action, the resource, the unit of measurement, and the key behavioral characteristic without wasting words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple (zero parameters) and has an output schema, so the description need not explain return values. It fully covers what the tool does, what it returns, and that invoking it has no balance cost. No important usage context appears to be missing.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has zero parameters, so the parameter semantics baseline is 4. The description correctly communicates that no inputs are needed and adds meaningful context by specifying the balance currency. There is no parameter documentation gap for the schema to compensate for.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Get') and names a precise, identifiable resource: the current rejestr.io API account balance in PLN. It cleanly differentiates itself from all sibling tools, which focus on organizations, persons, and financial documents rather than account state.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implicitly signals when to use this tool: whenever the agent needs to know the account balance. It also adds usage-relevant context by noting the call is free and does not consume the balance, which helps an agent decide to use it as a safe, non-destructive check before other API operations.

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

• get_organization_financial_documentA
  4.5/5.0
  Behavior5/5

  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, and it does so thoroughly. It reveals that PDF output saves a file to the downloads directory, returns an absolute path, optionally returns base64 content inline, and that JSON output returns parsed content directly. It also states the plan requirements and higher cost for JSON, which are critical behavioral details not visible in 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two compact, information-dense sentences. The first sentence states the core operation and resource; the second covers format variations, defaults, plan requirements, side effects, return behavior, and cost with no filler or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  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 no output schema, the description explains the return modes, file-saving side effect, inline content option, plan gates, and cost tradeoffs. The only minor omission is guidance on how to obtain the document_id through sibling list tools, but the description still provides enough to invoke the tool correctly for either format.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema only describes format and return_base64, leaving id and document_id with bare types, so the description meaningfully compensates by establishing that id identifies the organization and document_id identifies the financial document. It also enriches format and return_base64 with behavior, requirements, and cost implications. The added value is strong but not exhaustive for every parameter edge case.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb and resource: 'Get one financial document for an organization by document id.' The word 'one' and the identifier requirement clearly distinguish this from the sibling list_organization_financial_documents tool, and the format-specific behavior further clarifies what the tool does.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives good context for choosing between format='pdf' and format='json', including plan requirements, cost differences, and output behavior. However, it never explicitly says when to use this tool versus its siblings, such as using list_organization_financial_documents to find document IDs first. The guidance is useful but mainly 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.

• get_organization_krs_extractA
  4.5/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses side effects: it saves the PDF to a downloads directory, returns an absolute path, optionally returns base64 content, and enforces plan requirements. It also mentions an edge case where current extracts return 404 for deregistered organizations. This is strong behavioral transparency.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences cover the core action, plan requirements, side effects, return value, and optional base64 behavior. Information is front-loaded and every clause earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given three parameters, no annotations, and no output schema, the description is complete enough for an agent to call the tool correctly: it explains required output behavior, optional inline content, plan tiers, and a relevant failure case. Nothing critical is missing.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 67%, with extract_type and return_base64 already well documented in the schema. The description restates some of this information and adds the fact that the file is always saved to disk, but it does not clarify the id parameter beyond its name/type. The description adds some value but relies heavily on the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific action ('Download a KRS extract PDF') on a clear resource ('for an organization'). It immediately distinguishes the tool from siblings like get_organization_krs_chapter or list_organization_krs_entries by focusing on the downloadable extract artifact.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Provides clear usage context: which extract type requires which plan, and which type works for deregistered organizations. It does not explicitly compare against sibling tools, so it falls short of a full 5, but the current/full differentiation gives solid practical guidance.

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