RunOnProof

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

Annotations already indicate idempotent and non-read-only behavior. The description adds that the response preserves country-specific coverage, sources, freshness, and limitations, which is some useful output context. However, it does not disclose side effects of the approval action (e.g., record creation, status changes), so transparency remains limited.

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

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

The description is a single short sentence and not verbose. However, the phrase 'Global RunOnProof tool' is opaque jargon, and the sentence does not clearly convey purpose or behavior, limiting its value despite its brief length.

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 tool has a complex oneOf schema with many required fields and no output schema, yet the description provides almost no operational context. It does not explain what approving a supplier entails, how to choose between BR and GB variants, what the response looks like, or any prerequisites, making it severely inadequate for an agent to invoke 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%, and the only parameter mentioned is 'country from BR, GB', which is already present as an enum in the schema. The description provides no additional meaning for critical fields like cnpj, company_number, policy_id, idempotency_key, or the payee object, so it fails to compensate for the lack of documentation.

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 never states an explicit action like 'approve' or 'validate'; it labels itself 'Global RunOnProof tool' and instructs to choose a country, which does not clarify what the tool actually does. The phrase 'the response preserves...' hints at output characteristics, not the core purpose, leaving the function vague.

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 guidance or alternatives are mentioned. Although 'Global' and the country list imply multi-country coverage, siblings like approve_uk_supplier and run_uk_supplier_approval suggest overlapping functionality, and the description does not explain when to choose this tool over those.

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?

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds 'Paid' (cost implication) and 'Claims are limited to the named official sources' (a constraint on inputs/data), which is useful but ambiguous. No contradiction with annotations.

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 exceptionally short with only two sentences, no redundant wording. It is front-loaded with the operation identifier. However, the second sentence is cryptic and may not earn 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 tool with 7 parameters, nested objects, and many sibling operations, this description is grossly inadequate. It provides no operational context, no statement of what the tool does beyond the API name, and no guidance on outcomes, side effects, or usage scenarios. Even with an output schema present, the description fails to convey enough to use the tool 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 only 43%, and the description mentions no parameters at all. With low coverage, the description should compensate by explaining key fields like payee or idempotency_key, but it adds nothing. Agents must rely on the incomplete schema, leaving many parameters unexplained.

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 identifies the tool as a 'paid x402 UK tool for gb.supplier.approve.v1', which implies an approval action for UK suppliers, but it never explicitly states the purpose in plain language. It fails to clearly differentiate from siblings like approve_supplier, relying on the name rather than a clear verb+resource 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 provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or specific contexts. An agent selecting among many sibling tools receives no decision support.

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?

Annotations already declare the tool read-only, non-destructive, open-world, and idempotent. The description adds context about being 'public no-charge' and 'LIMITED' and that claims are limited to official sources, which provides some additional behavioral insight. No contradiction with annotations is present.

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 very short and to-the-point, but its brevity is due to under-specification rather than efficient conveyance of needed information. It lacks a clear statement of the tool's function, making it less useful despite being concise.

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 simple tool with no parameters and an output schema, the description is still incomplete. It does not clearly state what the tool assesses beyond the name, and it does not provide enough context for an agent to confidently invoke it. The existence of an output schema does not compensate for the lack of purpose clarity.

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, so schema coverage is automatically 100%. The description need not explain parameters, and per the rubric, a baseline of 4 is appropriate for a tool with no parameters.

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 mentions the tool is for 'gb.invoice.authenticity_duplication.assess.v1', which hints at assessing invoice authenticity and duplication, but it does not state this explicitly with a clear verb. It is not a tautology, but the purpose is somewhat vague and relies heavily on the tool name itself.

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

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

The description provides no guidance on when to use this tool versus its siblings. It mentions 'LIMITED' and 'claims are limited to named official sources,' which implies a constraint, but there is no clear context for selection or exclusion of alternatives.

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?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds that it is public/no-charge and limited to official sources, which is useful context, but it does not describe what the tool returns or other behavioral details such as output format or error conditions.

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

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

The description is a single sentence, which is concise, but it is cryptic and not front-loaded with a clear purpose. It uses technical identifiers like 'gb.source_evidence_freshness.assess.v1' without explanation, reducing clarity.

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 an output schema and annotations, the description is insufficient for an AI agent to understand when to use this tool, especially given many similar UK assessment tools. It lacks a clear plain-language statement of purpose and usage context, making it hard to select 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?

There are zero parameters, so the baseline is 4. The description does not add anything about parameters, but none need explanation. The schema has additionalProperties true, but with no parameters, this is not a significant gap.

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 references a model name but does not explicitly state that the tool assesses freshness of UK source evidence. It is vague and does not distinguish from sibling tools like assess_uk_invoice_authenticity_duplication. The name conveys action but the description relies on inference.

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 guidance is given on when to use this tool vs alternatives. The only additional info is 'Claims are limited to the named official sources,' which is a scope limitation, not usage guidance. It does not compare with siblings or state prerequisites.

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?

Annotations already convey readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds that the response preserves country-specific coverage, sources, freshness, and limitations, but this is vague and does not disclose side effects, required permissions, or the mutation inherent in payment authorization.

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 short, but it is poorly structured and front-loaded with the vague label 'Global RunOnProof tool'. The sentence about response preservation is ambiguous and does not communicate the tool's purpose or behavior 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?

Given the very complex input schema with oneOf branches, nested objects, idempotency keys, and vendor-change structures, the one-sentence description is grossly insufficient. It does not explain the tool's purpose, expected inputs, output format, or relationship to country-specific workflows.

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 description only addresses the country parameter and simply repeats the BR/GB enum already defined in the schema. It provides no information about the numerous required fields, nested objects, or oneOf structure. With 0% schema description coverage, the description fails to add any parameter semantics.

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 labels the tool as a 'Global RunOnProof tool' and instructs choosing a country, but never states that it authorizes payments or defines the tool's core function. It lacks a specific verb+resource construction and does not distinguish it from sibling tools like authorize_uk_business_payment.

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 only mentions the country choices (BR, GB) and provides no guidance on when to use this tool versus the many country-specific sibling tools. No prerequisites, exclusions, or alternatives are given.

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?

Annotations already declare non-read-only, idempotent, open-world, and non-destructive traits. The description adds that it is paid and that claims are limited to named official sources, which are useful but vaguely worded. It does not describe side effects 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.

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

The description is one sentence but prioritizes jargon over clarity. It is under-specified for a tool with a complex schema, lacking a clear structure or front-loaded purpose.

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 tool is highly complex with nested objects and 8 top-level parameters, yet the description provides almost no operational context. It does not explain the limited nature, the claim types, or how to use the tool in a workflow.

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 description makes no mention of any parameter. Schema description coverage is only 50%, leaving many nested fields undocumented in the schema, and the tool description does not compensate.

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 'Paid x402 UK tool for gb.business.payment.authorize.v1 (LIMITED)' is an endpoint reference rather than a plain-language statement of function. It relies on the tool name to convey the action, which is tautological. It does not clarify what 'claims' or 'LIMITED' mean.

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 guidance on when to use this tool versus siblings like authorize_payment or run_uk_payment_authorization. The description provides no conditions, prerequisites, or exclusion criteria.

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?

The description adds a few behavioral hints beyond the annotations, such as indicating a paid/quota-limited operation ('Paid x402') and restricting claims to 'named official sources.' However, it does not describe the authorization flow, side effects, or return behavior. The annotations already disclose idempotency and non-destructiveness, so the additional context is minimal but not contradictory.

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 highly compact, using just two short fragments with no unnecessary words. However, the cryptic phrasing ('Paid x402', 'LIMITED') and lack of a coherent sentence structure reduce clarity, preventing a perfect score.

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 a rich schema and an output schema, the description is insufficient for a tool of this complexity. It omits when to use the tool, what 'Paid x402' means, and how this differs from sibling authorization tools. The vague 'LIMITED' and 'named official sources' remain undefined, leaving significant gaps in context.

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 provides detailed descriptions for 83% of the parameters, including fingerprint rules, company number patterns, and the challenge object's nested fields. The description itself adds no parameter-specific semantics, so the baseline of 3 applies given the high schema coverage.

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 identifies the tool as authorizing UK vendor payment detail changes via the endpoint 'gb.vendor.payment_detail_change.authorize.v1', clearly conveying the action and resource. However, terms like 'Paid x402' and 'LIMITED' are unexplained, and it does not explicitly distinguish this from sibling tools such as 'authorize_uk_business_payment' or 'run_uk_vendor_change_continuous_authorization'.

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 offers no guidance on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or preferred contexts. The hints about 'LIMITED' and 'named official sources' are too vague to inform usage decisions.

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?

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds useful context: 'Metadata-only' confirms a non-mutating operation, 'authenticated HTTP operator access required' discloses access/prerequisites, and 'Claims are limited to the named official sources' reveals a constraint on data provenance. This exceeds what annotations alone provide.

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

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

The description is a single dense sentence that packs several concepts (metadata-only, authentication, UK scope, resource version, availability, claim source limits) without clear structure. It is not excessively long, but it is cryptic and not well front-loaded; key terms like 'Metadata-only' and 'AVAILABLE' are ambiguous.

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 an output schema and rich annotations, the description leaves the tool's core purpose ambiguous. It does not clarify whether the tool builds a passport, returns metadata about a passport, or something else. With zero parameters, the description should explain what the tool does and what the output represents, but it fails to do so convincingly.

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 input schema has 0 explicit parameters (additionalProperties true), so the baseline is 4. The description adds no parameter-specific information, but that is acceptable because there are no defined parameters to document.

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 is vague about what the tool actually does. 'Metadata-only' suggests it retrieves metadata rather than building anything, contradicting the tool name 'build_uk_company_capability_passport'. It references a resource but does not explicitly state the action or outcome, and it does not distinguish this from siblings like issue_company_passport or refresh_company_passport.

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 guidance is provided on when to use this tool versus alternatives. The phrase 'AVAILABLE' might indicate availability status, but it does not help an agent decide when to call this tool. There are no exclusions or alternative tool names mentioned.

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?

Annotations already declare the tool as read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds the 'Free:' context, which hints at no cost for invocation, and notes that it lists prices. This is useful but minimal additional behavioral insight beyond what annotations provide.

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

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

The description is a compact, front-loaded sentence: 'Free: list all capabilities and prices.' Every word contributes meaning, and the free indicator is immediately visible. There is zero waste, and the structure is easy to scan.

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 zero-parameter, no-output-schema tool with strong annotations, the description 'Free: list all capabilities and prices' fully captures the tool's functionality. It explains both the action and the subject, leaving no critical gaps for an agent to select and 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?

With zero parameters, the schema has complete coverage and the description doesn't need to explain any inputs. The baseline for 0-param tools is 4, as there is no parameter semantics to clarify. The description adds no parameter-related value, but none is required.

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

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

The description clearly states the action ('list') and the resource ('all capabilities and prices'), making its purpose immediately obvious. It distinguishes itself from sibling tools, which are all specific operations like verification or approval, by being the meta-tool for discovering what's available.

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

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

The description implies its usage: if an agent needs to know available capabilities or pricing, this is the tool. However, it doesn't explicitly state when to use it vs alternatives or provide exclusions. The sibling context makes the use case evident, but the description itself offers no direct guidance beyond its obvious purpose.

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?

Annotations already disclose readOnlyHint:false, destructiveHint:false, and idempotentHint:true. The description adds that the response preserves country-specific coverage, sources, freshness, and limitations, which is a useful behavioral detail. However, it does not disclose important side effects or the requirement for a previous_authorization object, leaving transparency 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?

The description is short but not effectively concise. The first sentence 'Global RunOnProof tool' is a vague label that adds no value, and the second sentence mixes an instruction with response characteristics. It is structured as two loose fragments without a clear logical flow, and the overall sparseness constitutes under-specification rather than concise clarity.

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 tool has a complex schema with oneOf branches, nested objects, and many required parameters for the BR branch, yet the description provides almost no context about the tool's operation, when to use it, or what the parameters represent. There is no output schema, and the description only vaguely references response preservation, leaving the agent with insufficient information to correctly invoke the tool.

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

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

Schema description coverage is 0%, so the description must explain parameters. It only mentions 'country' (already clear from the enum) and completely ignores critical parameters like 'previous_authorization', 'idempotency_key', 'cnpj', and 'policy_id'. No added meaning is provided for these fields, making it impossible for an agent to understand what values to supply.

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 labels it as 'Global RunOnProof tool' but never states the tool's actual action, such as continuing a vendor authorization. The phrase 'Choose country from BR, GB' is an instruction to the agent, not a description of what the tool does, leaving the core purpose ambiguous and indistinguishable from siblings like 'continue_vendor_authorization'.

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 alternatives. No scenarios, exclusions, or alternative tools are mentioned, despite the existence of similar sibling tools such as 'continue_vendor_authorization' and 'run_uk_vendor_change_continuous_authorization'. The description merely suggests choosing a country, which is not enough to determine appropriate usage.

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?

Annotations already declare readOnly, idempotent, openWorld, non-destructive. Description adds 'public no-charge' and a data-source limitation, which provides incremental context, though it doesn't explain expected behavior or output.

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

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

The description is a single short sentence, front-loaded with availability. It's concise but somewhat cryptic; still, it's appropriately sized for a zero-parameter 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 the tool's apparent role in a vendor authorization workflow, the description lacks a clear action statement and fails to convey why or how the continuation happens. The output schema exists but the purpose ambiguity undermines completeness.

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?

Tool has zero parameters, so the description has no parameter burden; the schema has no relevant content. Baseline 4 applies.

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

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

The description references an endpoint name 'vendor.authorization.continue.v1' and availability status but never states in plain language what the tool does. It doesn't differentiate from siblings like 'continue_vendor' or 'run_uk_vendor_change_continuous_authorization'.

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 guidance on when to use this tool or when to choose an alternative. The mention of 'claims limited to named official sources' implies a constraint but not usage context.

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?

The description adds the notable traits that the tool is paid via x402 and deterministic, which go beyond the annotations. However, it does not elaborate on the open-world side effects hinted by openWorldHint, leaving uncertainty about what external state may be affected.

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

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

The description is a single concise sentence with no redundant words, and the payment notice is front-loaded. Yet its extreme brevity sacrifices substantive information, which is a trade-off rather than an ideal structure.

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

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

Given the nested object input, missing output schema, and absent parameter descriptions, the one-line description is wholly inadequate for an agent to invoke this tool correctly. It doesn't explain the meaning of the inputs, the expected output, or the operational context.

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%, and the description contributes nothing about the 'subject' or 'counterfactual' parameters. The nested counterfactual object is entirely undocumented, and the description fails to compensate for the lack of schema-based explanations.

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 simply restates the tool name as 'counterfactual analysis' and adds a payment indicator, but does not state an explicit action or resource. It omits that the tool operates on a Brazilian CNPJ subject, leaving the purpose vague and indistinguishable from sibling tools.

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 usage context is given. The description provides no guidance on when to use this tool versus the many sibling verification or assessment tools, nor does it mention any prerequisites or scenarios.

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?

Annotations already indicate non-read-only, idempotent, and non-destructive behavior. The description adds 'Paid' and 'signed' but does not clarify side effects, required permissions, or consequences. It does not contradict annotations but provides minimal additional transparency beyond them.

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

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

The description is a single cryptic fragment, which is concise but under-specified. It lacks structure and fails to communicate essential meaning, so the brevity does not add value.

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 nested parameters and no output schema, the description is severely incomplete. It doesn't explain the return value, the notion of a 'signed decision', or what constitutes a valid request. This is inadequate for an agent to understand the tool's role.

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 coverage is 0%, so the description should compensate for explaining parameters. It only hints at 'objective-based' (relating to the objective field) but says nothing about the required 'subject' object or CNPJ. The cnpj field has a brief schema description, but the top-level semantics remain unexplained.

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 says 'objective-based signed decision for a Brazilian company' but lacks a clear verb or outcome. It doesn't explain what 'decide' actually performs or what a 'signed decision' entails. It is not a full tautology but is too vague to distinguish from sibling approval/verification tools.

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 guidance is provided on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or reference sibling tools. The cryptic 'Paid (x402)' hint offers no practical context for selection.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds 'Public no-charge' and 'LIMITED' as cost/limitation context, plus the statement about claims being limited to official sources. This adds some value beyond annotations, though it is vague and does not describe specific behaviors like rate limits or data freshness.

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

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

The description is a single, front-loaded sentence that conveys the key facts (public, no-charge, UK, API identifier) without wordiness. The final clause about claims is cryptic but adds some information, so it earns its place. One could argue for 5, but the cryptic nature slightly reduces clarity.

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 parameters, good annotations, and an output schema, the description fails to explain what the tool actually does or when to use it. 'Material change' is domain-specific and unglossed, and the 'named official sources' are not enumerated, leaving significant context for the agent to infer from the name alone. This is inadequate for a specialized tool amid many alternatives.

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, so the description does not need to explain parameter meaning. The schema is trivial (additionalProperties true) and coverage is 100%, so the baseline of 4 is appropriate because there is nothing for the description to add.

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 identifies the tool as a 'UK tool for gb.company.material_change.detect.v1', which implies it detects material changes in UK companies, but it never explicitly states the action or scope. It mentions 'Claims are limited to the named official sources' but doesn't clarify what 'claims' or 'material change' means, so it's understandable but not fully specific.

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 guidance is provided on when to use this tool versus its many siblings (e.g., verify_company_status, run_uk_company_check). The 'LIMITED' tag hints at a constrained use case but is not explained, and there are no exclusions or alternative suggestions.

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?

Annotations already indicate non-read-only, idempotent, and non-destructive behavior. The description adds only that the response preserves country-specific coverage, sources, freshness, and limitations, but fails to disclose side effects like record creation, authentication needs, or rate limits.

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 phrase 'Global RunOnProof tool' is uninformative and does not earn its place. The key information about country selection is buried after this filler, and the description lacks a clear front-loaded structure that immediately conveys the tool's purpose.

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 schema includes conditional requirements (BR needs cnpj, execution_ids, idempotency_key; GB only needs country), but the description does not address these complexities. There is no output schema, and the response behavior is only vaguely mentioned, leaving the tool under-specified for an agent to invoke 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 compensate for missing parameter meanings. It merely restates the country enum ('Choose country from BR, GB') and offers no explanation of cnpj, execution_ids, idempotency_key, or why the BR branch requires additional fields while the GB branch only needs country.

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 calls it a 'Global RunOnProof tool' without explicitly stating that it issues a company passport. The mention of country selection and response characteristics gives some hint, but the core purpose is vague and does not clearly distinguish it from sibling tools like verify_company_passport or refresh_company_passport.

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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, exclusions, or typical use cases, leaving the agent without contextual decision support.

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?

The description adds that the tool is paid and that claims are limited to named official sources, which is helpful context beyond the annotations. However, it does not explain side effects (readOnlyHint=false implies mutation) or expected behavior on match/no-match, so transparency is partial.

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 short (two sentences) but uses jargon like 'x402' and 'LIMITED' without explanation. While concise, it sacrifices clarity, and the structure is not as effective as it could be.

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

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

Given the tool has an output schema and nested parameters, the description is still too thin. It does not explain what the tool returns, when it should be invoked, or how it differs from many closely related sibling tools. An agent would struggle to use it correctly based solely on this description.

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 high (75%) with good parameter descriptions for company_number, payee_fingerprint, and idempotency_key, plus nested binding_evidence fields. The tool description itself adds no parameter-specific meaning, so the baseline of 3 applies.

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

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

The description references an endpoint name ('gb.business_payee.match.v1') and mentions claim limitations, but it never explicitly states what the tool does (e.g., matching a UK business payee to a company). It lacks a clear verb+resource statement, making the purpose vague and heavily dependent on the tool name.

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 guidance is provided on when to use this tool versus siblings like verify_uk_bank_account_ownership or match_uk_invoice_to_company. The only hints are 'UK tool' and 'limited', which do not help with selection decisions.

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?

The description adds an ambiguous statement about 'claims are limited to the named official sources' but does not explain what those sources are or what behavioral implications exist. With readOnlyHint false, the agent cannot infer side effects, and the cryptic 'Paid x402' reference does not clarify access requirements. Annotations partially cover idempotency and open-world hints, but the description contributes little beyond them.

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 short but not effectively concise—the first sentence reads like a status or pricing note rather than useful information, and the second sentence is cryptic. Every sentence should add value, but these sentences provide minimal functional context.

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

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

Given the tool has 5 parameters, a nested object, and an output schema, the description is severely incomplete. It does not communicate the core purpose, how parameters relate, or how to use the tool, making it inadequate for an agent to select and invoke 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 descriptions cover 80% of parameters, including formats and idempotency key usage. The description itself adds no parameter-specific meaning, so the baseline of 3 is appropriate because 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?

The description only refers to the endpoint identifier 'gb.invoice.company.match.v1' and a vague claim about 'official sources', without stating that the tool matches a UK invoice to a company. It fails to distinguish the tool from siblings like verify_uk_invoice_and_payee or match_uk_business_payee, offering no clear verb+resource description.

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 indication of when to use this tool over alternatives. It does not mention prerequisites, typical scenarios, or exclusions, leaving the agent without any guidance on tool selection.

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?

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that the tool is free, produces estimates, and specifies the output metrics, which provides useful behavioral context beyond the annotations. It does not cover rate limits or auth details, but that is not necessary given the 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?

The description is a single sentence that front-loads the key facts: 'Free', the verb 'estimate', the resource 'CNPJ', and the metrics. Every word contributes meaning, with no redundancy or 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?

The tool has only one parameter, rich annotations, and the description lists the output metrics. Given the simplicity of the tool and the absence of an output schema, the description is sufficiently complete for an agent to select and 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?

The input schema already fully describes the 'cnpj' parameter as 'Brazilian CNPJ (14 digits)' (100% coverage). The description only mentions 'CNPJ' without adding new syntax or format details, so it does not add significant value beyond the schema. Baseline 3 is appropriate.

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

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

The description uses a specific verb 'estimate' and identifies the resource (CNPJ) along with the specific dimensions (resolvability, coverage, confidence, price). It clearly distinguishes itself from sibling tools like 'resolve_legal_entity' or 'quote' by focusing on pre-payment estimation for a CNPJ, making its purpose unambiguous.

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 phrase 'before paying' provides a clear usage context, indicating the tool is a pre-payment check. However, it does not explicitly name alternative tools or state when not to use it, so it falls short of full guideline clarity. The context is clear enough to guide appropriate use.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior, covering the safety profile. The description adds the 'Free' cost aspect, which is a minor behavioral detail, but it does not explain return format, potential side effects beyond annotations, or other operational nuances.

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 extremely concise and front-loaded, with no redundant phrasing. However, it is under-specified to the point of ambiguity, so while there is no wasted text, the brevity is not fully appropriate for the tool's needs.

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 only one parameter, no output schema, and a minimal description, the tool is simple, but the description still omits essential context such as what the quote looks like, how 'capability' is identified, and any return values. The 'Free' prefix is not enough to make this complete.

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 only defines 'capability' as a string with no description, and schema description coverage is 0%. The description reuses the term 'capability' but does not clarify what values are expected, provide examples, or explain constraints, leaving the parameter largely opaque.

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

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

The description uses 'quote' as a specific verb and 'capability' as the resource, giving a rough sense of purpose. However, it does not define what a 'quote' is in this context or what the tool returns, leaving the meaning ambiguous and not clearly distinguishing it from sibling tools beyond the name.

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

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

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. It simply states 'Free: quote for a capability' without explaining scenarios or comparing to related tools.

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

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

The description adds useful context beyond the annotations by noting the tool is 'Paid (x402)' and that it performs an 'incremental refresh', which implies a specific side-effect profile. Annotations already cover idempotency and non-destructiveness, so the description complements them without contradiction.

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

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

The description is a single sentence, front-loaded with the most critical information ('Paid (x402)') followed by the action and resource. Every word earns its place, with no redundant or filler content.

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 tool is simple with one parameter, but the absence of an output schema and the description's silence on return values, prerequisites, or failure conditions leave gaps. The 'incremental' aspect is mentioned but not elaborated. Annotations partially compensate, but the description alone is minimally sufficient.

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

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

The schema has one parameter 'passport_id' with 0% description coverage. The description mentions 'passport/decision' but does not explicitly link it to the parameter. The parameter name is self-explanatory, and the description implies it identifies the passport to refresh, but the mapping is not explicit.

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

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

The description clearly states the action 'incremental refresh' and the resource 'passport/decision', which is specific and informative. However, it does not explicitly differentiate from sibling tools like 'refresh_company_passport' or 'verify_passport', leaving some ambiguity about scope.

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 term 'incremental refresh' implies a use case where an existing passport/decision needs updating, but the description provides no explicit when-to-use guidance or mention of alternative tools. It relies on the reader to infer the appropriate context.

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?

The description says 'Create a new immutable Passport version', which indicates a write operation, while annotations set readOnlyHint=true. This is an annotation contradiction. Additionally, the description introduces jargon like 'fresh committed execution set' without elaborating on behavioral implications like permissions, side effects, or lifecycle.

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

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

The description is a single sentence that is concise and front-loaded with the primary action ('Create a new immutable Passport version'). Every phrase adds meaning, and there is no 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?

The core behavior is clear, and annotations provide safety context, but the description lacks parameter explanations, return value information, and context about what constitutes a 'fresh committed execution set'. For a tool with 3 required parameters and no output schema, this is a gap in completeness.

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 coverage is 0% and the description does not explain any of the parameters (country, passport_id, idempotency_key). The phrase 'declared fresh committed execution set' is vague and does not map to the parameters, leaving the agent without guidance on what values to provide.

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

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

The description clearly states the tool's function: creating a new immutable Passport version from a fresh committed execution set, with reuse of unchanged claims. This distinguishes it from sibling tools like issue_company_passport or verify_passport, making its purpose specific and unique.

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 a prerequisite (declared fresh committed execution set) and the context of refreshing a passport, but it does not explicitly state when to use this tool versus alternatives such as refresh or verify_passport. No exclusions or alternative guidance is provided.

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?

Annotations already declare idempotentHint=true and readOnlyHint=false; the description adds that the response 'preserves country-specific coverage, sources, freshness and limitations,' which gives some behavioral context. However, it does not clarify side effects or authorization requirements. No contradiction with annotations.

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 short and to the point, but the first sentence 'Global RunOnProof tool' is jargon and the second sentence primarily lists response characteristics. It is not bloated, but the content is thin.

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

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

Given the complex oneOf schema with per-country required parameters, the description is underspecified: no mention of idempotency key requirements, what resolution returns, or how to handle US (which has no required params beyond country). This is insufficient for an AI agent to use the tool confidently.

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 description only mentions the country selector, which is already an enum in the schema. It provides no meaning for cnpj, company_name, company_number, postal_code, or idempotency_key, and with 0% schema coverage the description does not compensate.

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 identifies this as a 'Global RunOnProof tool' and says to choose a country, but never states what 'resolve' actually does (e.g., look up, verify, or match a legal entity). It does distinguish from siblings by naming BR, GB, US, but the core action remains vague.

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 no guidance on when to prefer this over the many sibling tools like resolve_uk_legal_entity or verify_company_status. It implies a global scope by listing countries, but does not specify scenarios, exclusions, or alternatives.

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?

Annotations already provide idempotent and non-destructive hints. The description adds value by disclosing the paid nature and that claims are limited to named official sources. However, it does not clarify the meaning of 'claims' or explain side effects given readOnlyHint=false.

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 very brief—two short sentences—and front-loads the paid status and availability. It is concise without being verbose, though the cryptic phrasing reduces clarity.

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 only four parameters, an output schema, and many siblings, the description is insufficient. It lacks usage context, prerequisite information, and a clear statement of the tool's core function. The 'claims' phrasing is vague and not elaborated.

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 coverage is only 50% (company_number and idempotency_key have descriptions; company_name and postal_code do not). The description does not compensate by explaining the anyOf requirement (provide company_number OR company_name) or the purpose of postal_code. It adds no parameter-level meaning.

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 primarily restates the operation name and version ('gb.legal_entity.resolve.v1') and status ('AVAILABLE'), but never states plainly what the tool does (e.g., 'resolve UK legal entity details'). The added note about claims being limited to official sources hints at behavior, not purpose.

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 guidance on when to use this tool versus the many siblings, especially the generic 'resolve_legal_entity' or other UK-specific verification tools. The description does not mention prerequisites or alternative selection criteria.

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?

The description adds some behavioral context beyond annotations by noting that the tool is paid and that 'claims are limited to the named official sources.' This hints at cost and output constraints. However, it is minimal and does not cover return format, side effects, or error behavior. Given the annotations already cover safety and idempotence, this is acceptable 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?

The description is extremely brief, but brevity here results in under-specification rather than conciseness. The first sentence is cryptic and does not earn its place, while the second adds only vague context. It fails to provide essential information in a structured way.

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

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

Given the tool has four parameters, an output schema, and many sibling tools, the description is incomplete. It does not explain what data the check returns, what 'claims' means, or how it relates to other verification tools. The agent is left without sufficient context to make an informed choice.

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 50%, covering company_number and idempotency_key but not company_name or postal_code. The description provides no additional parameter meaning, so the un-described parameters remain ambiguous. It does not compensate for the schema gaps.

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 essentially restates the tool name: 'Paid x402 UK tool for gb.solution.company_check.v1' is an internal reference that does not clarify what the tool actually does. It lacks a specific verb and resource, and does not distinguish it from sibling tools like verify_uk_company_status or run_uk_supplier_approval.

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 guidance is given on when to use this tool versus its alternatives. The description does not mention any use cases, prerequisites, or exclusions. An agent would have no idea whether to choose this over related UK company tools.

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

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

Annotations already cover read-only/mutating, idempotency, and destructiveness. The description adds that the tool is paid via x402 and that claims are limited to named official sources, which is useful but vague. No contradiction with annotations.

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 very short (two sentences) with no redundancy, but the content is under-specified and cryptic. It is concise in length but lacks substantive structure or clear front-loaded 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?

Given the highly complex schema with nested objects, vendor_change, and 8 parameters, a two-sentence description is grossly incomplete. It fails to clarify the core function, exact constraints, or typical usage scenarios, despite the presence of an output schema.

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 description provides no information about the 8 parameters, nested objects, or required idempotency_key. Schema coverage is only 50%, and the description does not compensate, leaving many parameters (e.g., supplier.vat_number, eori_number) without semantic clarity.

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 vaguely identifies it as a 'Paid x402 UK tool' for a solution identifier, but does not state a clear verb+resource. It fails to distinguish from sibling payment authorization tools like 'authorize_uk_business_payment' or 'authorize_uk_vendor_payment_detail_change'.

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 guidance is provided on when to use this tool versus alternatives. The constraint about 'named official sources' is mentioned but not actionable, and there is no mention of prerequisites or exclusions.

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?

The annotations already indicate idempotent and open-world behavior, and the description adds a few hints such as 'Paid' (cost) and 'Claims are limited...' (a restriction). However, it fails to disclose what side effects occur, what 'claims' means in this context, or whether any state is mutated. The description is too cryptic to convey meaningful behavioral traits beyond the annotations.

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 terse, but it contains redundant or unclear phrases. 'gb.solution.supplier_approval.v1' essentially restates the tool's name, and '(AVAILABLE)' appears to be a status flag rather than useful guidance. The second sentence is cryptic. While there is no excessive length, the content does not earn its place fully.

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

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

Given the complex input schema with nested objects (payee, binding_evidence) and 7 parameters, the description is severely incomplete. It does not explain the workflow, prerequisites, or what 'claims' refers to. The presence of an output schema helps with return values, but the overall guidance is inadequate for an agent to correctly select and invoke this tool.

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

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

Schema description coverage is only 43%, and the tool description does not compensate by explaining any parameters. It mentions no details about company_number, policy_id, idempotency_key, or the nested payee structure. Some parameter descriptions exist in the schema itself, but the description adds zero value beyond that.

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 does not clearly state what the tool does. It references an internal identifier 'gb.solution.supplier_approval.v1' and calls itself a 'Paid x402 UK tool', but never explicitly says it approves or runs a supplier approval workflow. It does not distinguish itself from sibling tools like approve_supplier or approve_uk_supplier, which likely have overlapping purposes.

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

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

No guidance is provided for when to use this tool versus the many alternatives. The phrase 'Claims are limited to the named official sources' hints at a constraint but does not explain when this tool is appropriate, what alternatives exist, or what conditions should trigger its use.

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?

Annotations already cover read-only, idempotent, and destructive hints. The description adds a few non-schema facts: 'Paid' (cost implication) and 'claims are limited to named official sources' (source scope). These are vague and do not disclose what happens on success or failure, required permissions, or why claims are limited, leaving a mutation tool's behavior opaque.

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 one short, structurally clean sentence, but it is under-specified to the point of being a label. It restates an internal solution name and a vague policy, offering almost no useful content, so it fails to earn 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?

This is a complex mutation tool with a nested object, idempotency, and a paid/limited access model, yet the description provides no contextual framing. It does not explain what a continuous authorization vendor change is, when to use it, or what the output means, especially given many closely related sibling tools.

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 coverage is only 50%, and the description provides no parameter information. It does not clarify the 'change' object, the idempotency key, or how to construct nested fields, so the agent must rely solely on field names and patterns without additional semantic help.

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 does not state what the tool does with a verb or resource. It merely repeats the name as a solution identifier ('gb.solution.vendor_change_continuous_authorization.v1') and adds a cryptic note about claims being limited to official sources, which does not explain the tool's function or distinguish it from siblings like authorize_uk_vendor_payment_detail_change.

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 alternatives. The 'Paid' and 'LIMITED' notes imply constraints but do not explain use cases, prerequisites, or exclusions, leaving the agent without any decision support.

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?

Annotations already cover read-only, idempotent, non-destructive safety. The description adds context beyond annotations: public/no-charge status and that claims are limited to named official sources, which tempers expectations and discloses scope boundaries. This is useful, though it could elaborate on what 'claims' means.

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

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

The description is a single, front-loaded sentence that packs key attributes (public, no-charge, UK, official source limitation). It avoids unnecessary detail but includes some cryptic elements like '(AVAILABLE)' and the version string, which add little value. Overall, it is concise and structured appropriately.

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 no parameters and an existing output schema, the description should focus on the tool's role and limitations. It provides essential UK scope and official-source restriction but does not differentiate from closely related siblings or explain how to identify the target business party. In a crowded sibling ecosystem, this is a clear gap.

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

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

The tool has zero defined parameters and no required inputs, and the schema uses additionalProperties: true. The description says nothing about expected inputs, but with 0 params the baseline is 4. The permissive additionalProperties without guidance could be confusing, but the tool likely relies on context rather than explicit parameters.

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

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

The description clearly identifies this as a UK tool for restricted_business_party.screen.v1, implying screening of restricted business parties. It also distinguishes from the sibling 'screen_restricted_party' via 'UK' and 'business' scope and the official-sources limitation. However, it lacks a direct verb like 'screens' or 'checks', relying on the version string and name.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. It mentions 'Claims are limited to the named official sources,' which hints at a limitation but gives no direction on selection. Given many sibling screening tools, this is insufficient.

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?

Annotations already cover idempotency and non-destructiveness; the description adds that the response preserves country-specific coverage, sources, freshness, and limitations, which is some behavioral context. However, it does not disclose potential side effects despite readOnlyHint=false, leaving significant gaps.

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 short and front-loaded, but the first sentence ('Global RunOnProof tool') adds no real information and reads as marketing fluff. The second sentence provides a bit of utility but doesn't compensate for the overall vague wording.

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?

This is a complex tool with a oneOf schema, country-specific required parameters, no output schema, and many sibling alternatives. The two-sentence description is grossly inadequate for helping an agent select and invoke the tool correctly, especially for the BR branch with required cnpj and idempotency_key.

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%. The description only mentions the 'country' parameter, which is already fully defined by the schema enum. It fails to explain the BR branch requirements (cnpj, idempotency_key) or the aliases/legal_name parameters, leaving the complex oneOf structure completely undocumented.

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 does not state a clear action; 'Global RunOnProof tool' is vague product language and does not explain that this tool screens restricted parties. It fails to distinguish from sibling tool 'screen_restricted_business_party', making the purpose ambiguous.

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 only guidance is to choose a country from BR or GB, which is a parameter constraint, not a usage guideline. There is no mention of when to use this tool versus the many UK-specific tools or the similar 'screen_restricted_business_party'.

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?

Annotations declare readOnly, openWorld, and idempotent hints, and the description adds context about being no-charge and limited to named official sources. This provides some operational insight beyond annotations, but does not elaborate on limitations or behavior in detail.

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 two concise sentences, front-loaded with key qualifiers (public, no-charge, limited), and contains no redundant content. It is appropriately sized for the tool's simplicity.

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 sparse and leaves ambiguity about what 'LIMITED' means and which 'named official sources' are referenced. However, the presence of an output schema and no parameters reduces the need for extensive detail, making it minimally sufficient but not thorough.

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, so schema coverage is trivially complete. The description does not need to explain parameter semantics, and the baseline for no-parameter tools is 4.

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 identifies the tool as a UK business document validation tool via the versioned identifier 'gb.business_document.validate.v1', implying a specific validation function. It is clear but does not explicitly distinguish it from sibling validation tools like verify_uk_business_licence.

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 guidance on when to use this tool versus alternatives. The description only notes it is public and no-charge, and mentions its limited scope, but does not provide selection criteria or exclusions.

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?

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds further behavioral context: no source calls, no charge, and it verifies the 'current' immutable passport. This goes beyond the annotations without contradicting them.

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 sentence with no filler. The verb, object, and qualifiers are front-loaded, and every phrase adds distinct information about the tool's behavior.

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 adequate for selecting the tool but lacks details on return values, result semantics, or error conditions. Since there is no output schema, the agent is left to infer what 'verify' actually returns. Basic context is present, but gaps remain.

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%, and the description does not explain the two required parameters (country, passport_id) beyond their names. With such low coverage, the description fails to compensate by clarifying formats, validation, or the role of the country enum.

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

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

The description clearly identifies the action (verify), the specific resource (Company Capability Passport), and key qualifiers (current, immutable, without source calls/charge). This distinguishes it from sibling tools like verify_passport, issue_company_passport, or refresh_company_passport.

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 phrase 'without source calls or charge' provides a clear contextual use case: verify a passport cheaply and without external dependencies. It does not explicitly name alternatives or exclusions, but the context is strong enough for an agent to infer when this tool is appropriate.

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?

The description mentions that the response preserves country-specific coverage, sources, freshness, and limitations, which is a response trait but not a behavioral disclosure. Given readOnlyHint=false, the tool may have side effects, yet the description does not clarify what side effects occur, nor does it mention authentication, rate limits, or idempotency behavior beyond the annotations. This is a significant gap for a tool that sounds read-only ('verify').

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 very short, but it is not well-structured: 'Global RunOnProof tool' is a sentence fragment that introduces unexplained terminology, and the rest of the sentence mixes input guidance with output characteristics. The core action is not front-loaded, and the semicolon use creates a run-on feel. It is concise but lacks clarity.

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, so the description's note about preserving coverage/sources/freshness/limitations is helpful but vague. The tool has complex country-specific input variants (three oneOf options with different required fields: BR needs cnpj, GB needs company_number, US needs only country), and the description does not explain these differences or what the actual verification result looks like. The agent is left to parse the schema for essential context.

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 description only mentions the country parameter selection; it provides no explanation of the cnpj, company_number, or idempotency_key parameters that appear in the oneOf variants. Some schema descriptions exist (e.g., for GB company_number and idempotency_key), but the description adds no extra meaning and does not compensate for low schema coverage, leaving the agent to rely entirely on the schema.

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

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

The description identifies the tool as a 'Global RunOnProof tool' and specifies the selectable countries (BR, GB, US), which gives a clear scope and distinguishes it from UK-specific siblings like verify_uk_company_status. However, it does not explicitly state the core action 'verify company status' – that is inferred from the tool name – and 'RunOnProof' is unexplained jargon.

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 offers clear positive usage context: it is a global tool and tells the user to choose a country from BR, GB, US. It does not explicitly reference alternatives or state when not to use the tool, but the 'Global' label and country list imply a broader scope than the UK-only siblings, providing adequate guidance.

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?

The description adds a useful behavioral trait: 'the response preserves country-specific coverage, sources, freshness and limitations.' This goes beyond the annotations, which already cover read-only/destructive/idempotency hints. However, it does not disclose the core verification behavior or potential side effects, so it only partially contributes.

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 short, but brevity is not conciseness when sentences are vague and low-value. The first sentence 'Global RunOnProof tool' contributes no useful meaning, and the second sentence is about response behavior rather than purpose. It is not well-structured for an agent to extract actionable guidance.

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

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

Given the highly complex input schema with oneOf branches, multiple nested objects, and no output schema, the description is severely incomplete. It provides no overview of the tool's operation, no return format, no parameter help, and no differentiation from sibling tools. The agent would be largely dependent on the schema, which is not enough for effective tool selection and invocation.

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 compensate for parameter understanding, but it does not. It only repeats the country choices already present in the schema. The complex oneOf branches with many required fields (cnpj, payee, invoice, idempotency_key) are completely undocumented.

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 does not state a clear action or resource. 'Global RunOnProof tool' uses undefined jargon, and the rest of the sentence focuses on country selection and response characteristics rather than what the tool actually verifies. It fails to differentiate from siblings like verify_uk_invoice_and_payee, relying entirely on the tool name for purpose.

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 phrase 'Choose country from BR, GB' implies that the tool is used for those countries, which is a vague usage signal. However, there is no explicit guidance on when to use this tool over alternatives, no exclusions, and no prerequisites. The guidance is implied but not clearly 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds minimal behavioral context beyond that, such as the 'signed' requirement, but does not disclose error behavior, return format, or other side effects. No contradiction with annotations.

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

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

The description is a single, concise sentence that is front-loaded with the verb and resource. It is efficient and free of fluff, though it may be too minimal for the tool's complexity.

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

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

Given the tool has a nested object parameter, no output schema, and many similar siblings, the description is too brief. It does not explain how verification works, what makes a passport 'signed', what the success/failure criteria are, or what the agent should expect in return. Significant gaps exist for an AI agent to correctly invoke and interpret 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?

With 0% schema description coverage, the description carries full burden for explaining the 'passport' parameter. It only says 'signed decision passport', which gives a hint but lacks structure, required fields, or format details. The description adds little over the bare schema.

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

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

The description clearly states the tool verifies a signed decision passport, using a specific verb and resource. It distinguishes from siblings like verify_company_passport by specifying 'decision passport', though it doesn't explicitly differentiate from all siblings.

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 guidance is provided on when to use this tool versus alternatives such as verify_company_passport or verify_uk_company_status. There is no mention of prerequisites, exclusions, or specific scenarios where this tool is the appropriate choice.

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?

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side-effect expectations. The description adds no extra behavioral context, such as failure modes or output semantics, so it meets the baseline without enhancement.

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

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

The description is a single, focused sentence with no redundant words. The 'Free:' prefix is slightly extraneous but does not detract, and the core instruction is front-loaded.

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 the description does not state what the tool returns (e.g., a boolean, a receipt status, or details). Given the tool's narrow scope and the lack of output information, the description is incomplete for an agent to fully understand the result and use the tool 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?

The schema provides zero description for the single 'receipt' parameter, and the description only identifies it as a 'signed decision receipt.' This gives a general type but lacks details about required fields, structure, or format, offering only partial compensation for the 0% schema coverage.

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

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

The description clearly identifies the action (verify) and the resource (a signed decision receipt), which is more specific than sibling verify tools that target different resources. However, it does not elaborate on what verifying entails, so it stops short of a full 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?

The description provides no guidance on when to use this tool versus alternatives like verify_passport or verify_uk_company_status. The 'Free:' prefix hints at cost but is not a usage directive, and no exclusions or prerequisites are mentioned.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds useful context: it is public/no-charge and results are limited to named official sources. However, 'SOURCE_CONDITIONED' is undefined, and the description doesn't disclose failure modes or edge cases.

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 compact (two sentences) and front-loads cost/availability. However, it prioritizes peripheral details over a clear statement of functionality, making it less effective as a prompt for correct usage.

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 zero parameters and an output schema, the description doesn't need to explain return values, but it fails to give a clear operational description. Key terms ('SOURCE_CONDITIONED', 'named official sources') are left undefined, and the actual verification behavior is assumed from the tool name. For a tool with many siblings, this is insufficient.

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 input schema defines zero parameters, so the baseline is 4. The description adds no parameter-level detail, but since there are no expected inputs, this is acceptable. The mention of 'SOURCE_CONDITIONED' implies some dependency on source data, but no specific parameters are required.

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 does not state a clear verb+resource action. It identifies the tool as a versioned UK verification service ('gb.bank_account_ownership.verify.v1') and notes a constraint on claims, but never explicitly says it 'verifies ownership of a bank account.' This borders on tautology with the tool name and offers no differentiation from sibling verification tools.

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 guidance on when to use this tool over siblings like verify_uk_company_status or verify_uk_business_licence. It only mentions it's public/no-charge and source-conditioned, but no context for when to call it or what alternatives exist.

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?

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds that the tool is public, no-charge, limited, and that claims are restricted to named official sources. This provides useful context about data scope and availability beyond the structured annotations.

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 extremely short—two sentences—and front-loads key facts (public, no-charge, UK). Every word earns its place, and there is no redundancy. It is exemplary in conciseness.

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 a clear name, the description does not explain the tool's purpose or its relationship to sibling verification tools. It fails to tell the agent when to invoke this instead of verify_uk_company_status or verify_uk_business_licence. The limitation about official sources is helpful but does not resolve the ambiguity.

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, so the schema is trivially complete. The description adds no parameter details, but the baseline for 0-parameter tools is 4, and there is nothing to compensate for.

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 identifies the tool as a UK tool for a specific API version but does not explicitly state that it verifies beneficial ownership or control. The verb 'verify' appears only in the technical version string, and no clear resource is described. It adds limited context (public, no-charge, limited) but the core purpose remains vague.

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 the many sibling UK verification tools. It does not mention selection criteria, prerequisites, or alternatives. The only hint is 'UK tool,' which is insufficient to distinguish it from verify_uk_company_status, verify_uk_business_licence, etc.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior, covering safety and idempotency. The description adds valuable context beyond annotations: it is public and no-charge, and results are SOURCE_CONDITIONED, meaning the output may depend on external data sources and claims are restricted to official sources. This clarifies limitations and conditional behavior.

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

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

The description is a single, front-loaded sentence that efficiently communicates the UK scope, public/no-charge nature, and source-limited claims. There is no filler or redundant repetition of the tool name, and it packs multiple relevant facts into minimal words.

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

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

The description leaves important details undefined: 'SOURCE_CONDITIONED' and 'named official sources' are cryptic and not explained, and it does not indicate what input should be provided to invoke the tool. The presence of an output schema covers return values, but the minimal description may still leave an agent uncertain about how to call this tool 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?

With zero parameters defined in the schema, the baseline is 4. The schema has additionalProperties: true, implying arbitrary inputs are allowed but not specified. The description does not add details about expected input fields, but there are no schema properties to document, so the description does not need to compensate. It neither clarifies nor contradicts the open schema.

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

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

The description names the specific resource (UK business licence) and includes the tool identifier 'gb.business_licence.verify.v1', which implies the verification action. It distinguishes from sibling tools like verify_company_status and verify_uk_tax_registration by focusing on business licences. However, the action verb is not explicitly stated in a full sentence, relying partly on the tool name.

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

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

The description provides no explicit when-to-use guidance or mention of alternatives. It states a constraint ('Claims are limited to the named official sources') but does not indicate when this tool should be preferred over other verification tools. Without guidance on alternatives, agents may not know how to choose among the many verify_* siblings.

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?

Annotations already provide idempotentHint, openWorldHint, and non-destructive flags. The description adds useful context by noting that the tool is 'Paid' and that 'Claims are limited to the named official sources,' which conveys cost and source-restriction behavior. However, it does not elaborate on what 'claims' means or what happens on failure, and mentions no side effects beyond what annotations imply.

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 very short, which is good for conciseness, but the first sentence is cryptic due to the endpoint-like string and the '(AVAILABLE)' marker. The second sentence is also vague ('Claims' is ambiguous). It is not verbose, but it sacrifices clarity for brevity, making it only average in structure.

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

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

Given the crowded sibling list with many verify/check tools, this description is insufficiently complete. It does not explain what 'legal status' verification entails, what official sources are named, or how this differs from generic verify_company_status. The presence of an output schema reduces the need to describe return values, but the missing usage differentiators and vague 'Claims' language leave a significant completeness gap.

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

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

Schema description coverage is 100%, with both company_number and idempotency_key well documented in the input schema. The description adds no additional parameter-level meaning, so the baseline score of 3 is appropriate: the schema handles parameter semantics and the description does not need to compensate.

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 does not state in plain language what the tool does. It references an endpoint identifier 'gb.company.legal_status.verify.v1' and the tool name carries the meaning, but a new agent would not be clearly told that this verifies UK company legal status. It provides some differentiation via 'UK' and 'legal_status' but not enough to be considered a clear purpose 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 offers no explicit guidance on when to use this tool versus alternatives like verify_company_status or run_uk_company_check. The 'UK' qualifier implies applicability to UK companies, but there are no exclusions, prerequisites, or alternative recommendations. The phrase 'Claims are limited to the named official sources' hints at a constraint but does not clarify usage.

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?

The description adds that the tool is paid and that claims are limited to named official sources, which is useful context beyond the annotations. However, it does not disclose any side effects, return behavior, or operational nuances, and the annotations already cover safety hints (idempotent, non-destructive).

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 only two sentences and contains no fluff. It is front-loaded with key facts (paid, UK, formal solution ID) but the first sentence is somewhat cryptic due to the solution ID and 'LIMITED' acronym. Overall, it is concise and efficient.

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 nested object inputs, an output schema, and many sibling verification tools, this description is critically incomplete. It does not explain what the tool does, why it is used, how to structure inputs, or what the output represents. The sparse description cannot support correct selection or invocation.

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 coverage is only 33% (only idempotency_key has a top-level description), and the description provides zero parameter clarification. The tool has complex nested parameters (invoice, payee) with many fields, but the description does not explain their purpose or expected semantics, leaving the agent to infer from field names alone.

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 identifies this as a UK invoice/payee verification tool via the solution ID, but it never explicitly states the action ('verifies', 'validates') or what the verification entails. It relies heavily on the tool's name. The added phrase 'Claims are limited to the named official sources' gives some scope but does not clearly distinguish it from sibling verification tools.

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 alternatives. It only says claims are limited to official sources, which weakly implies usage for official verification, but no exclusions or alternative tool references are provided.

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?

Adds value beyond annotations by disclosing that the tool is public, free, and limited to official sources, which informs reliability expectations. However, 'SOURCE_CONDITIONED' is undefined, and the behavior when sources are unavailable is not explained.

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

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

The description is a single concise sentence, but it relies on cryptic jargon like 'SOURCE_CONDITIONED' and the model identifier, which may reduce clarity. Overall, it is appropriately brief and front-loaded with key facts.

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 incomplete for a verification tool with an output schema. It does not mention what the output represents, how to interpret claims, or when to use it among the many sibling verification tools. It only covers cost and source limitations.

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, so the description adds no parameter semantics, but the baseline for zero-parameter tools is 4. The schema allows arbitrary additional properties, yet the description does not address this.

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 identifies the tool as a UK tax registration verification service via the model reference 'gb.tax_registration.verify.v1', but does not explicitly state what action it performs or what it verifies. It also fails to distinguish this tool from sibling verification tools like verify_uk_company_status.

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 guidance is provided on when to use this tool versus alternative verification tools. The description mentions 'public no-charge' and source constraints, but does not indicate use cases, prerequisites, or situations where this tool should be preferred.

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