Server Quality Checklist

Tool Scores

• validate_eoriB
  3.2/5.0
  Behavior2/5

  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. It states only the purpose ('Validate') without revealing how validation works, whether it consults external systems, what happens on invalid input, or what the response structure contains. This is a significant gap for a tool that likely performs network-backed checks.

  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, compact sentence that front-loads the core purpose and provides contextual variation. There is no wasted wording, and it communicates the essential function immediately.

  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 is simple with one parameter, but the absence of annotations and low param coverage leaves important aspects unaddressed—e.g., whether validation is synchronous, if there are rate limits, or error behavior. The presence of an output schema mitigates return-value explanation, but overall the definition is only minimally complete for a validation tool.

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

  Parameters2/5

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

  The input schema provides no description for the eori_number parameter, and schema coverage is 0%, so the description must compensate. It mentions the authorities but does not explain the expected format (e.g., country prefix + digits, length, examples). The parameter meaning is self-evident from the name, but the description adds no syntax or validation rules beyond that.

  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 tool validates an EORI customs number, a specific resource type, and it names the relevant authorities (EU via EC, GB via HMRC, XI for Northern Ireland). This distinguishes it from sibling validation tools like validate_vat or validate_iban, which handle different identifier types.

  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 on when to use this tool versus alternatives. It does not mention prerequisites, whether it performs format-only or live lookups, or exclusions (e.g., 'use for EORI only'). The context of siblings implies usage, but the description leaves the decision entirely to inference.

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

• lookup_company_by_vatB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. It only states the action (lookup) without disclosing whether it is read-only, what happens on invalid or unmatched VAT numbers, or any rate-limit or authentication requirements. For a lookup tool, this omission is noticeable, though not as severe as for a mutation tool.

  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 sentences with no redundant words. The main purpose is front-loaded in the first sentence, and the second provides essential usage context. Every phrase earns its place.

  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?

  An output schema exists, so return-value details need not be in the description. The description covers the core use case and fallback scenario, but it omits potential edge cases like non-German/Spanish VAT numbers or error behavior. Given the single parameter and the presence of an output schema, this is adequate but not thorough.

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

  Parameters2/5

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

  Schema coverage is 0% for the single parameter 'vat_number'. The description mentions 'by VAT number' but does not specify the expected format (e.g., country code prefix, digits only, length). It adds only minimal meaning over the schema's type string and title, leaving the agent to guess the exact input format.

  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 gives a specific verb and resource ('Look up company data by VAT number') and adds the GLEIF cross-reference to clarify the source. It clearly distinguishes itself from siblings like validate_vat and lookup_company_by_lei by focusing on company data retrieval rather than validation or LEI-based lookup.

  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?

  It states a clear condition for use: as a fallback for German/Spanish VAT numbers when VIES returns no company name/address by law. This tells the agent when to use it, though it doesn't explicitly name alternative tools to prefer (e.g., validate_vat for validation). The context is clear but not as explicit as a direct sibling-routing statement.

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

• lookup_company_by_leiB
  3.4/5.0
  Behavior2/5

  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. It states a lookup action, which implies read-only, but does not explicitly mention that it has no side effects, what happens if the LEI is invalid or unknown, any rate limits, or authentication requirements. A read-only tool with no annotation coverage should disclose more.

  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. It front-loads the action and resource, then specifies the identifier and source. Every word contributes value.

  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 is simple (single parameter) and has an output schema, so the description does not need to detail return values. However, it omits failure modes (e.g., LEI not found) and any other runtime behavior. For a basic lookup, this is acceptable but not fully complete given the absence of annotations.

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

  Parameters2/5

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

  Schema coverage is 0% (the LEI parameter has no description in the schema), so the description must compensate. It mentions 'by LEI' and lists the output fields, but does not provide format constraints, length, or validation rules for the LEI input. The description adds minimal semantic meaning beyond the parameter name itself.

  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 ('look up'), the resource ('company data'), and specifies the identifier ('by LEI') and the source ('via GLEIF'). It names the fields returned (legal name, address, status), which distinguishes it from sibling toolkit tools like lookup_company_by_vat.

  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 for LEI-based lookups but does not explicitly differentiate from siblings or state when to prefer this over lookup_company_by_vat. The purpose is clear enough for an agent to infer the right context, but explicit guidance on alternatives or exclusions is missing.

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

• get_vat_ratesA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description alone must convey behavior. It states it returns 'current' rates and specifies 'standard/reduced', which gives some behavioral context. However, it does not disclose expected behavior for invalid or non-EU codes, error handling, or whether only one rate or both are always returned. Since the output schema exists, some of this may be covered there, but the description could add more behavioral detail.

  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 that front-loads the action and resource. It contains no filler or redundancy, and every word adds value.

  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 one-parameter lookup tool with an output schema, the description covers the essential purpose, scope, and parameter format. It does not mention edge cases like non-EU territories (e.g., EEA), but the tool is straightforward and the description is adequate for an agent to invoke it 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 description coverage is 0% for the only parameter (country_code), so the description must supply meaning. It does so by specifying the format ('ISO 3166-1 alpha-2') and the scope ('EU country'), which goes well beyond the bare schema type 'string'. This is sufficient for the single parameter.

  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 ('VAT rates') and scopes it to 'EU country' with a defined code format ('ISO 3166-1 alpha-2'). This clearly distinguishes it from sibling tools like validate_vat or lookup_company_by_vat, which are about validation and company lookup, not rate retrieval.

  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 clearly situates when to use the tool: when you need current standard and reduced VAT rates for an EU country. It does not explicitly mention alternatives or exclusions, but the context is unambiguous, and sibling tools are semantically distinct enough that no further guidance is strictly needed.

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

• validate_ibanA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden. It discloses that the validation is offline (MOD-97), that it covers all SEPA countries, and that it accepts spaces in the input—all useful behavioral traits beyond the schema. It does not mention error handling or edge cases, but for a simple validation tool the coverage is good.

  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 with no fluff. The core purpose is front-loaded, with scope and input-format details in the second sentence. Every word earns its place, making it highly efficient for an agent to parse quickly.

  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?

  Given the tool's simplicity (one parameter) and the presence of an output schema, the description is largely complete. It covers offline behavior, SEPA scope, and input formatting. It omits explicit error-handling behavior, but that is not critical for a validation tool and the output schema likely captures return semantics.

  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?

  Despite 0% schema description coverage, the description compensates by specifying that the IBAN may be provided with or without spaces, which is a concrete input-format requirement. The single parameter is clearly the IBAN string, and the description adds enough semantic detail to guide correct usage.

  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 verb (validate) and resource (IBAN), and clarifies it performs an offline MOD-97 checksum while also resolving bank name and BIC. This clearly distinguishes it from sibling validation tools like validate_vat and validate_eori, leaving no ambiguity about its function.

  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 by naming the IBAN resource, but does not explicitly state when to choose this tool over siblings, nor does it provide exclusions or alternatives. The SEPA coverage hint adds context but does not formally differentiate use cases, so it falls short of explicit guidance.

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

• check_service_statusA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of visibility. It discloses that the endpoint is public and works without an API key, implicitly signaling no authentication requirement and a read-only (non-mutating) nature via 'check'. It does not mention rate limits or response specifics, but for a simple health-check tool with an output schema, the disclosed behavior is sufficient.

  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 tight two-sentence structure. The first sentence states what the tool does, and the second gives usage context and an example. There is zero filler; every word 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 the tool's zero-parameter signature, a straightforward read-only purpose, and the presence of an output schema, the description covers everything an agent needs to call it correctly. The example clarifies the diagnostic intent, and no further context is necessary.

  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 there is nothing to explain. The baseline for zero parameters is 4, and the description adds no parameter-related 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 states a clear verb ('Check') and a specific resource ('live health of upstream government services'), and enumerates the exact services (VIES, EORI, HMRC, GLEIF). This unambiguously distinguishes the tool from its sibling validation and lookup tools (e.g., validate_vat, lookup_company_by_vat), which all perform different operations.

  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 explicitly tells the agent when to use it: 'Use it to explain why a validation returned reduced confidence' and gives a concrete example (Germany's VIES endpoint down). It also notes that it is a public endpoint requiring no API key. However, it does not explicitly state when not to use it or name alternative tools, so it misses the full 'when/when-not/alternatives' bar for a 5.

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

• validate_vatA
  4.8/5.0
  Behavior5/5

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

  With zero annotations, the description carries full responsibility for behavioral disclosure. It exceeds this bar by detailing return fields (validity, company name/address, confidence level, source), noting that Germany and Spain never expose address data, and explaining input parsing (prefix optional, Greece accepts EL/GR). This gives the agent a clear picture of behavior without needing annotations.

  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 succinct sentences plus an example. It front-loads the purpose, then returns, then input handling. Every clause earns its place; there is no redundant phrasing or filler.

  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 the tool's complexity (multiple return fields, edge cases, parameter flexibility) and the absence of annotations, the description covers all necessary ground: what it does, what it returns, how inputs are parsed, and known exceptions. The presence of an output schema reduces the need to detail return structures, but the description does anyway. No critical information is missing.

  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?

  Schema description coverage is 0%, so the description must explain both parameters. It does so explicitly: vat_number can include a prefix or not, and country_code is an optional complement (e.g., 'DE123456789' or '123456789' + country_code='DE'). The Greece EL/GR note further clarifies country_code accepted values. This compensates fully for the lack of schema descriptions.

  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 'Validate an EU or UK VAT number via VIES/HMRC', a specific verb and resource that immediately distinguishes it from siblings like validate_iban, validate_eori, and lookup_company_by_vat. The return fields and input flexibility further clarify its unique role among the sibling tools.

  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 clearly states the tool's scope (EU or UK VAT) and what it returns, which makes its intended use obvious. However, it does not explicitly name alternatives or provide 'when not to use' exclusions. The lack of direct sibling comparisons is a minor gap, but the purpose is specific enough that an agent can infer when to invoke it.

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