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

Without annotations, the description should disclose behavioral traits such as side effects or required permissions. It only states the action and parameters, omitting details like whether it modifies subscription status, triggers billing, or is reversible.

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 concise, combining a purpose statement with a parameter list in a single sentence. It is front-loaded with the action and endpoint, though it could be better structured (e.g., bullet points) for 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?

Given the tool's complexity (7 parameters, no output schema, no annotations), the description lacks context about post-addition effects, return values, or implications for the subscription. It fails to provide a complete picture for an AI agent to use 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?

Since schema coverage is 100%, the baseline is 3. The description adds minor value by explaining the required 'productRatePlanId' and briefly describing 'ratePlanCharge' structure, but does not significantly expand on parameter meanings beyond 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 clearly states the action ('Add a rate plan to a subscription') and includes the HTTP endpoint, making the purpose unambiguous. It distinctively differs from sibling 'add_subscription_rate_plan_charge' by focusing on adding a rate plan 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 only lists parameters and does not provide guidance on when to use this tool versus alternatives like 'add_subscription_rate_plan_charge' or 'update_subscription_rate_plan'. No when-not conditions 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?

With no annotations, the description discloses key behaviors: it is a POST (creating), notes required fields, highlights conditional requirements for billingPeriodAlignment/specificBillingPeriod when chargeType is recurring, and explains special handling of the weight parameter (multiplied by 100). Missing side effects or error conditions, but covers substantial behavioral details.

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 paragraph. It front-loads the purpose but becomes a run-on list of requirements. While efficient, it lacks structure (e.g., bullet points) and could be slightly more concise. Still, every sentence adds 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?

The tool has 17 parameters, no output schema, and complex constraints. The description thoroughly covers input requirements and conditional fields, but fails to mention return values, success/failure indicators, or error handling. This is a notable gap for a creation tool with no 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?

Schema coverage is 100%, so baseline is 3. The description adds meaningful context beyond schema: grouping required fields, explaining the weight conversion, and clarifying the chargeTier array structure. This extra information helps the agent understand parameter usage beyond the schema descriptors.

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 ('Add a rate plan charge to a subscription rate plan') and provides the POST endpoint. It lists the purpose and required fields, but does not explicitly differentiate from sibling tools like `create_product_rate_plan_charge` which might be confused.

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 alternatives (e.g., `add_subscription_rate_plan` or `create_product_rate_plan_charge`). It does not state prerequisites or when not to use it, leaving the agent without decision support among many 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?

No annotations provided; description only mentions HTTP method and parameter list. Does not disclose side effects, idempotency, error handling, or whether calculation logs anything.

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

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

Two sentences, front-loaded with action and endpoint. Efficient listing of required/optional params.

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

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

No output schema and no annotations; description omits what the response contains (rates, carriers, etc.). For 15 parameters, more context on assumptions and return structure is needed.

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

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

Schema description coverage is 100%, so baseline is 3. Description restates parameter names but adds no new meaning beyond the schema field descriptions.

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?

Clearly states the action 'calculate shipping rates' and the resource, using a specific verb-noun pair. No other sibling tool performs this function, so it is distinct.

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 vs alternatives. Lists required/optional parameters but does not explain preconditions or typical 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?

No annotations provided, so the description carries the full burden. It mentions it's a POST request and charges an invoice, but does not disclose side effects (e.g., invoice status change, payment recording), error conditions, or idempotency. This is insufficient for a mutation tool.

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

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

The description is concise, front-loads the action and endpoint, and presents key details (cents, required fields, payment type guidance) without wasted words. Every sentence adds 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?

Given no output schema and simple parameters, the description is mostly adequate but lacks mention of prerequisites (e.g., invoice must be unpaid), typical response, or error cases. It covers the basics but leaves some gaps.

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

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

Schema coverage is 100%, but the description adds value beyond schema: clarifies 'amount' is in cents with an example, explains paymentType options, and recommends thirdPartyPaymentProvider for card/online. This aids correct parameter usage.

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 charges an invoice via card/online payment, specifies the POST endpoint, and distinguishes from siblings like charge_invoice_external by implying it's for internal payment types. The verb 'charge' and resource 'invoice' are 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 description gives guidance on paymentType values (e.g., 'Use thirdPartyPaymentProvider for card/online') but does not explicitly state when to use this tool versus alternatives like charge_invoice_external. Usage context is implied but not contrasted with 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?

With no annotations, the description provides the HTTP method (POST) and endpoint, and clarifies the amount format (cents). It does not disclose side effects, errors, or idempotency, but for a simple charge operation, the information is adequate.

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

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

The description is very concise with three sentences. It leads with the core purpose, includes the HTTP method and endpoint, then provides critical parameter details. No unnecessary 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 covers the essential aspects: action, payment type, endpoint, and parameter format. However, it does not mention the return value or outcome of the operation, which could aid the agent in understanding the full 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 covers both parameters with descriptions (100% coverage). The description adds valuable context by explicitly stating 'AMOUNT IN CENTS' with an example (5500 = $55.00), which clarifies the unit beyond the schema's generic description.

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

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

The description clearly states the tool's action ('Charge an invoice') and specifies the payment method ('offline payment (cash/check/wire)'). It also provides the API endpoint, distinguishing it from sibling tools like 'charge_invoice' which likely handles other payment methods.

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 explicitly mentions offline payment, indicating the context of use. It does not list alternatives or when not to use, but the mention of 'offline payment' gives clear guidance 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?

No annotations provided, and the description lacks behavioral details such as idempotency, error handling, or side effects. Only the HTTP method and required parameters are mentioned.

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?

Extremely concise with two sentences, front-loaded with the main action. No unnecessary 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?

Given no output schema and no annotations, the description is too minimal. It does not explain return values, error conditions, or post-creation behavior.

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 100%, but the description merely repeats the required parameters without adding meaning or constraints beyond what the schema already documents.

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 ('Create a company currency') and the resource ('currency'), distinguishing it from sibling tools like get_currency, update_currency, etc.

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 vs alternatives (e.g., update_currency). The description only states the action without context on 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?

With no annotations present, the description must disclose behavioral traits. It reveals the HTTP method and field requirements but omits side effects (e.g., duplicate email handling), idempotency, authorization needs, or error 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 two concise sentences, front-loaded with the core purpose, and contains no extraneous 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?

While the description covers input parameters, it lacks information about the output (e.g., returns created customer ID) and does not address potential conflicts or limitations, leaving gaps despite the tool's simplicity.

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 100% with descriptive parameter descriptions. The description restates required/optional fields, adding minimal value beyond 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 clearly states the action ('Create a new customer'), includes the HTTP method and endpoint, and lists required and optional fields. This distinguishes it from siblings like create_currency or create_invoice, which serve different entities.

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

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

The description implies the tool is for creating customers but does not specify when to use it versus alternatives like update_customer, nor does it provide exclusions or context-dependent 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?

No annotations are present, so the description must fully disclose behavior. It only lists fields but does not mention idempotency, required customer existence, response format, or error 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 brief and front-loaded with the action and endpoint, but listing all fields adds redundancy given the schema.

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

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

No output schema is provided, and the description does not specify what is returned upon creation or potential errors, leaving the agent uninformed about 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?

Schema coverage is 100% with each parameter described. The description mostly repeats schema info but adds minimal value, such as listing required fields and country code format.

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?

Clearly states 'Create an address book entry for a customer' and provides the HTTP endpoint, distinguishing it from sibling tools like update_customer_address or delete_customer_address.

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?

Implies usage for creating new addresses but does not explicitly state when to use versus alternative tools, nor provides 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?

No annotations are provided, so the description bears full responsibility. It mentions the API endpoint (POST) and important notes about amount units and conditional weight requirement. However, it does not disclose other behavioral traits such as side effects, idempotency, authorization needs, or error handling.

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 concise and well-structured, front-loading the purpose and endpoint, then providing a clear list of required/optional parameters. It avoids unnecessary verbosity but could be slightly more streamlined.

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 10 parameters, no output schema, and no annotations, the description covers the essentials but lacks information about return values, error scenarios, and idempotency. It is adequate for a creation tool but not fully 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 covers 100% of parameters, so baseline is 3. The description adds value by emphasizing that amount is in cents with examples, clarifying that weight is required when category is physical, and listing required vs. optional parameters in a readable way.

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 purpose: 'Create a charge or credit for a customer.' It uses a specific verb and resource, distinguishing it from siblings like delete_customer_charge_credit and list_customer_charges_credits.

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 specifies required and optional parameters but does not explicitly state when to use this tool over alternatives. However, it is clear that this is for creating a charge/credit directly, unlike other tools for charging invoices. No exclusion criteria are given, but the context is adequate.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool is gateway-agnostic, does not accept raw card data, and requires a single-use token. It doesn't discuss mutation side effects or return format, but it is transparent about the data handling and integration path.

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 three sentences, front-loaded with the purpose. The second sentence lists required fields, and the third explains the token workflow. While efficient, there is minor redundancy (e.g., 'Gateway-agnostic:' repeats info from schema). Still, it is well-structured for quick parsing.

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 covers purpose, workflow, and parameters. However, with no output schema and no mention of return values (e.g., created payment method object or ID), the agent lacks information about the tool's output. For a creation action, this is a notable gap, lowering 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 100%, baseline 3. The description adds value by explaining the workflow for paymentMethodNonce, specifying that billingAddress requires countryCode, street1, city, state, zip (with street2 optional), and clarifying type values ('card or ach'). This goes beyond the schema field descriptions.

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 purpose: 'Create a payment method for a customer.' It specifies gateway-agnostic nature and enumerates required fields. This differentiates it from sibling tools like update_customer_payment_method, delete_customer_payment_method, and get_customer_payment_method.

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 a clear workflow: obtain gateway client credential via get_client_token, use a payment integration to produce a paymentMethodNonce, then call this tool. It does not explicitly state when not to use this tool or mention alternatives, but the prerequisites and process are well explained.

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

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

No annotations provided, so description carries full burden. It only indicates creation but lacks details on permissions, idempotency, side effects, or what happens on success/error.

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?

Single sentence with key details and a list of required fields. Concise without unnecessary words, though could be slightly more structured with separate sections.

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

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

No output schema, yet description does not mention return value or response. Lacks constraints like uniqueness or allowed values for section (only gives examples). Incomplete for a creation 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 coverage is 100%, so baseline 3. Description adds a bit by listing required fields and explaining the rules structure, but mostly repeats schema info.

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 'Create a company filter' with the endpoint and required fields. It is specific to creation, but does not differentiate from siblings like 'list_filters' or 'remove_filter'.

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 alternatives (e.g., updating or deleting filters). No context on prerequisites or typical use cases.

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

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

No annotations provided, so description carries burden. It discloses that it creates via POST, required fields, and prerequisite steps, but does not mention idempotency, error handling, or authorization requirements.

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?

Single paragraph that front-loads purpose and then details prerequisite and parameter construction. Every sentence adds value, but could be slightly more concise without losing 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?

Given complexity (5 params, nested object, no output schema), description covers prerequisite, required/optional fields, and setting construction. Lacks error handling or response details, but adequate for creation 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 coverage is 100%, but description adds meaning by explaining how to construct setting with keys from list_global_gateways, and clarifies that card is array of card type IDs and paymentMethod may be required by API.

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?

Clearly states it creates a company gateway, specifies HTTP method POST and endpoint, and distinguishes from sibling tools like delete_gateway and update_gateway by focusing on creation.

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?

Explicitly instructs to call list_global_gateways first to discover valid gblGatewayId and required setting keys, and notes that paymentMethod may be required by API. Lacks explicit when-not-to-use alternatives but provides strong 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?

With no annotations, the description carries the transparency burden. It discloses unit handling ('Tool always sends cents to publicAPI') but omits other behavioral traits like idempotency, error handling, or side effects.

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 paragraph that efficiently conveys purpose and parameters. It is front-loaded but could be more structured (e.g., using bullet lists). No redundant sentences.

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 18 parameters, nested objects, and no output schema, the description adequately covers required/optional, constraints, and unit behavior. It lacks response details but that's acceptable without 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?

Schema coverage is 100%, baseline 3. The description adds value by grouping required/optional, specifying max lengths, ISO country code, and valid enumeration values (e.g., paymentType, type), and clarifying amount unit conversion.

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 'Create an invoice' and specifies the HTTP method 'POST /invoices'. It lists required and optional parameters, distinguishing it from siblings like charge_invoice or update_invoice.

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 (e.g., charge_invoice, create_subscription). No explicit context or exclusions are given, leaving the agent to infer appropriateness.

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?

Without annotations, the description carries full burden. It discloses mutation via 'POST' but omits behavioral details such as idempotency, error states, response format, or side effects (e.g., duplicate handling).

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

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

Two sentences, front-loaded with the main action, then a bullet list of fields. Efficient but could be trimmed by not repeating schema names.

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

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

No output schema or annotations exist. The description lacks return value information, error handling, and authentication context. For a CRUD operation with 5 parameters, it is incomplete.

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

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

Schema coverage is 100%, so the schema already documents parameters. The description restates required vs optional but adds no additional constraints, valid values, or formatting rules beyond what the schema provides.

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

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

The description clearly states the action ('create'), the resource ('product'), and the HTTP method ('POST'). It distinguishes from siblings like 'update_product' or 'create_product_rate_plan'.

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 implicitly indicates usage for creating a product but offers no guidance on when to use this tool vs alternatives like 'create_product_rate_plan' or 'update_product'. No explicit 'do not use' conditions.

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

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

No annotations provided, so the description must fully disclose behavior. It states it's a POST operation to create a resource but omits details on side effects, permissions, error conditions, or idempotency. The disclosure is minimal.

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 concise with two sentences that front-load the purpose and include key parameter groups. It is well-structured but could be more accurate by listing all optional parameters.

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 12 parameters, no output schema, and no annotations, the description is incomplete. It fails to explain return values, handle error cases, or provide relational context with sibling tools like create_product_rate_plan_charge. Significant 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 100%, so baseline is 3. The description adds value by listing required fields and enumerating type values (contract|ongoing|prepaid) not explicitly in the schema. However, it omits several optional parameters (e.g., minimumCommitmentLength, changeStatusBasedOnCharge) that are present in the schema, which could mislead.

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 'Create a rate plan' with a verb and resource. It also mentions the HTTP method and endpoint. However, it does not explicitly differentiate from sibling tools like create_product_rate_plan_charge, though the naming implies the difference.

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 alternatives (e.g., update, list). There is no mention of prerequisites or context that would help the agent decide to use this tool over others.

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

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

No annotations are provided, so the description must carry full behavioral disclosure. It only lists input parameters without mentioning side effects, permissions, rate limits, or response behavior. The agent gains little insight beyond what the input schema already provides.

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 dense block of text listing parameters, which is acceptable but not concise. It front-loads the core purpose but then becomes a parameter dump. Every sentence earns its place, but the structure could be improved for readability.

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 24 parameters, no output schema, and no annotations, the description is incomplete. It does not explain the return value, error conditions, or how this tool fits into the larger workflow (e.g., must be called after creating a rate plan). Sibling tools imply a broader context, but the description lacks such guidance.

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 100% description coverage, so the description adds minimal extra semantic value beyond repeating field descriptions. It provides some inline examples (e.g., URI for ratePlanId), but this does not significantly enhance understanding beyond 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 clearly states 'Create a rate plan charge' and provides the endpoint POST /product-rateplan-charges, effectively distinguishing this tool from sibling create tools like create_product_rate_plan or create_subscription.

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 lists required and optional fields but does not explicitly state when to use this tool versus alternatives. Sibling tools include many create operations for different entities, but no guidance is provided on when to create a rate plan charge versus other related actions.

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 states that the tool works via the gateway endpoint and returns a setupIntent.id that can serve as a paymentMethodNonce. It also warns 'No raw card data.' However, it lacks details about side effects, failure modes, or the distinction between creating and retrieving. For a tool with no annotations, the description carries full burden and could be more transparent.

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 consists of two sentences that are concise and front-loaded. The first sentence states the action, and the second provides usage context. Every sentence adds value, though it could be slightly more structured.

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 role in a payment flow with only 2 parameters and no output schema, the description covers purpose and usage. However, it does not explain the 'create or retrieve' behavior in detail or specify the return structure, leaving some gaps.

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

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

The input schema has 100% coverage with descriptions for both parameters ('Company gateway ID (required)', 'Customer ID (required)'). The description does not add extra parameter-specific details beyond the schema, so it meets the baseline of 3.

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

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

The description clearly states the action ('Create or retrieve a setup intent') and the resource ('via the gateway endpoint'). It distinguishes its purpose by noting it's part of a 'gateway-agnostic payment method flow' and references a sibling tool ('create_customer_payment_method'). However, the 'or retrieve' phrasing introduces some ambiguity about whether it always creates or can retrieve an existing one.

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 explicitly states when to use this tool ('Use only as part of a gateway-agnostic payment method flow') and provides a concrete next step ('the returned setupIntent.id can be used as paymentMethodNonce for create_customer_payment_method'). It does not explicitly state when not to use, but the context is clear enough.

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

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

No annotations are provided, so the description must carry the full burden. It does not disclose side effects, idempotency, what happens to existing subscriptions, or whether the operation is reversible. It only mentions required inputs.

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 short sentences, front-loaded with the purpose, followed by required fields. It is concise and to the point, with no unnecessary 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?

There is no output schema, and the description does not explain what the tool returns (e.g., subscription ID, success message). For a creation operation with 5 required IDs, the description lacks information about validation, default values, or behavioral outcomes.

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

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

Schema description coverage is 100%, and the description essentially repeats the parameter list and required status. It adds little beyond the schema, so the baseline of 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 clearly states the action ('Create a subscription') and the resource ('from a product rate plan'), with the HTTP endpoint included. This distinguishes it from sibling tools like add_subscription_rate_plan or create_product_rate_plan, which have different 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?

The description lists required fields but provides no guidance on when to use this tool versus alternatives. There is no mention of prerequisites, conditions, or why one might choose this over other subscription-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?

With no annotations, the description carries full burden. It discloses that the operation fails conditionally (if in use), which is critical behavioral info. It lacks details on auth, rate limits, or success response, but for a delete, the provided failure conditions are sufficient.

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

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

Two sentences, no filler. Purpose is first, followed by failure conditions and endpoint. Every word earns its place.

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

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

For a simple delete with one parameter and no output schema, the description covers purpose, endpoint, and failure conditions. It could mention success response (e.g., HTTP 204), but that is often implied. Mostly 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?

Schema coverage is 100% with a description 'Company currency ID (required)'. The description adds only the URL pattern and route, which is marginal 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 explicitly states 'Delete a company currency' and provides the HTTP method and endpoint, clearly distinguishing it from create, update, and get currency tools. The action and resource are 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 description implies when NOT to use it by noting it fails if the currency is in use (invoices, subscriptions, etc.), but does not provide explicit alternatives or a clear 'when to use' statement. However, the context is clear enough for most agents.

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

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

With no annotations, the description fully discloses the destructive behavior and cascading effects on related data (addresses, payment methods, etc.), plus the HTTP method. This is excellent transparency.

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

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

Two sentences: first states purpose and method, second warns about consequences. No unnecessary words, and key info 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?

For a simple delete operation with one parameter and no output schema, the description covers purpose, method, and side effects adequately. No 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 coverage is 100% with a clear description for customerId. The tool description adds no extra meaning beyond what the schema provides, so baseline score 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 clearly states the verb 'Delete' and the resource 'customer by ID', and includes the HTTP method. It distinguishes from sibling delete tools by being specific to customer deletion.

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 warning about cascading delete provides context for when to use (with caution) but does not explicitly state alternatives or when not to use. The guidance is clear enough for decision-making.

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

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

No annotations are provided, and the description only mentions 'Delete' with no disclosure of side effects, irreversibility, required permissions, or cascade behavior. The tool is destructive but lacks behavioral context.

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?

Extremely concise with one sentence and the REST endpoint. Every word adds value, but it could be front-loaded with behavioral notes without becoming verbose.

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 delete tool with two required parameters and no output schema, the description lacks information on return value, error handling, or success confirmation. It meets minimal completeness but leaves gaps.

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

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

Schema coverage is 100% with clear parameter descriptions (customerId and addressId as required strings). The tool description adds no extra meaning beyond the schema, so a baseline of 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 clearly states 'Delete an address book entry' with the HTTP method and path, directly indicating the action and resource. It distinguishes from sibling tools like create_customer_address, update_customer_address, and get_customer_address.

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 alternatives (e.g., create, update, or other deletion methods). The description simply states the action without context on 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?

With no annotations, the description carries full burden. It reveals that the operation is destructive and specifies one failure condition (invoice details assigned). However, it does not mention what happens on success or other potential side effects, which is informative but not exhaustive.

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 sentences, front-loading the action and then the condition. Every sentence provides essential information with 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?

Given the lack of annotations and output schema, the description covers basic purpose and a key constraint. It does not describe return values, permissions, or idempotency, leaving some gaps for a straightforward delete operation.

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 100% coverage, describing both parameters as required IDs. The description adds no additional meaning beyond the schema, so it meets the baseline of 3.

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

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

The description clearly states the action ('Delete') and the resource ('charge or credit for a customer'), and includes the REST endpoint. It distinguishes from siblings like 'create_customer_charge_credit' and 'list_customer_charges_credits'.

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 a clear precondition: the charge/credit must not have invoice details assigned. It implies when not to use the tool, but does not explicitly mention alternatives or provide a complete usage strategy.

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

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

No annotations are present. The description only states 'Delete' and the HTTP endpoint, with no information about reversibility, required permissions, or consequences (e.g., impact on subscriptions).

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?

Extremely concise, two sentences, and front-loaded with the core action. Every word adds value, 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?

For a deletion tool with no annotations or output schema, the description lacks necessary safety and behavioral context. Critical information about side effects or prerequisites is missing.

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 100%, with both parameters described in the input schema. The description adds no additional meaning beyond what the schema provides, meeting the baseline.

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 'Delete a payment method' with a specific verb and resource, and the HTTP DELETE URL confirms the action. It distinguishes itself from sibling tools like create/get/update/list.

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 alternatives, no mention of prerequisites or side effects. The purpose implies deletion but lacks contextual decision-making 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?

No annotations are provided, so the description carries full burden. It discloses the failure condition but lacks details on permissions, side effects, or reversibility, which are important for a destructive operation.

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

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

Two concise sentences with no redundant information. The description is front-loaded with the action and endpoint.

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 one-parameter delete tool, the description is adequate but does not mention return values or success response. Since there is no output schema, a brief note on output would improve 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?

The single parameter 'gatewayId' is described in the schema, and the tool description adds context by showing it as a path parameter. This adds value beyond the schema description.

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

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

The description clearly states it deletes a company gateway and provides the REST endpoint, distinguishing it from create_gateway, update_gateway, and other 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?

It includes a condition that deletion fails if the gateway is linked to currencies or customers, guiding when to use or avoid. However, it does not explicitly state when to use this tool over other delete 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?

No annotations are provided, and the description does not disclose behavioral traits beyond the basic action. It does not state whether the operation is irreversible, what permissions are required, or if there are any side effects like cascading deletions. For a destructive operation, this is a significant gap.

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 concise at two sentences, including the HTTP method and path. It is front-loaded and contains no extraneous information. However, it could be slightly more structured, e.g., by separating the action from the endpoint reference.

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 delete operation with one parameter and no output schema, the description is minimally adequate. It states the action and the required parameter but lacks context about effects on related resources, error conditions, or comparison to similar tools like void_invoice. Given the complexity, additional context would be beneficial.

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 100% coverage with the single required parameter 'invoiceId' described as 'Invoice ID (required)'. The description adds no additional meaning, such as expected format, where to obtain the ID, or any constraints. Baseline score 3 applies due to full 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 states 'Delete an invoice', which is a specific verb+resource. It distinguishes from sibling tools like create_invoice, update_invoice, and void_invoice by indicating the delete action. However, it lacks any further clarification about the scope or consequences of deletion.

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 such as void_invoice or charge_invoice. It does not specify prerequisites, such as the invoice needing to exist or be in a deletable state, nor does it mention any conditions under which deletion 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?

Explicitly mentions cascading deletion and HTTP method, providing key behavioral info beyond just 'delete'. No annotations, so description carries burden.

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?

Three concise sentences covering purpose, method, and important warning; no wasted 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?

Adequate for a simple delete tool with one parameter; warning about cascading is critical. Could mention return type but not essential.

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?

Single 'productId' parameter with 100% schema coverage; description adds no additional meaning beyond schema description.

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

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

Clearly states 'Delete a product' with HTTP method and path. Unambiguous about what resource is affected.

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?

Warning about cascading deletion adds context for when to use cautiously, but no explicit when-to-use vs alternatives (e.g., delete_product_rate_plan).

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

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

No annotations are provided, so the description must disclose behavioral traits. It only says 'Delete', implying destruction, but does not mention any side effects (e.g., cascade deletions), irreversibility, or required permissions.

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

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

The description is extremely concise with two short sentences, no redundancy, and front-loads the action. Every word earns its place.

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

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

Given the tool's simplicity (one parameter, delete operation) and lack of output schema, the description is adequate but lacks behavioral context such as return type or effects. It is minimally 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 input schema has 100% description coverage for the single parameter, explaining it as 'Rate plan ID (URI: /product-rateplans/{ratePlanId})'. The description adds no additional meaning beyond what the schema already provides.

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

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

The description clearly states 'Delete a rate plan' with a specific verb and resource, and includes the HTTP method and path, distinguishing it from siblings like create, update, or list rate plan 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?

The description provides no guidance on when to use this tool versus alternatives, such as prerequisites or consequences of deletion. It only states what it does, leaving the agent without context for appropriate invocation.

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

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

With no annotations to rely on, the description must disclose behavioral traits. It only states that the tool deletes a charge but does not mention irreversibility, cascading effects, validation requirements, or the nature of the operation (e.g., soft vs hard delete). This is insufficient for safe invocation.

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, comprising a single sentence and the HTTP endpoint. It is front-loaded with the core action and resource, contains no filler, and is well-structured for quick comprehension.

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 lack of output schema and annotations, the description should compensate by explaining expected outcomes (e.g., whether it returns the deleted object or a confirmation, success/error handling). It does not provide this, leaving the agent under-informed about the result of the operation.

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 covers the single parameter 'chargeId' with a description 'Rate plan charge ID'. The tool description adds no further meaning beyond the schema, which already achieves 100% coverage. The baseline of 3 is appropriate as no extra semantic value is provided.

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 ('Delete') and the resource ('rate plan charge'), making the purpose unambiguous. The inclusion of the HTTP endpoint further reinforces the specific operation, and the name is distinct among sibling delete 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?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or conditions under which deletion is appropriate. Without such context, an agent may misuse the tool.

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

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

No annotations are provided, leaving the description as the sole source. It does not disclose behavioral traits like irreversibility, impact on associated data, permissions needed, or immediate vs. deferred deletion.

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?

Three concise sentences: action, endpoint, and a crucial warning. No filler, front-loaded with key 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?

For a deletion tool with no annotations and no output schema, the description should cover side effects, permanence, and more detail on when deletion is appropriate. It only warns about alternative usage.

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 100% for the single parameter subscriptionId, which already has a description. The tool description adds no additional semantic value beyond what the schema provides.

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

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

The description clearly states it deletes a subscription and provides the HTTP endpoint. It explicitly distinguishes from the sibling update_subscription_status by warning to prefer archiving over deletion for ending subscriptions without removing records.

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 explicitly advises when to use archiving (update_subscription_status) instead of deletion, but does not specify when deletion itself is appropriate or under what circumstances it should be used.

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

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

With no annotations provided, the description carries full burden. It explains that the tool returns markdown and defaults to overview. However, it does not discuss error handling, what happens with invalid doc parameter, or any limitations. The mention of 'so Claude can read...' gives context but not detailed behavioral traits.

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 sentences, front-loaded with the primary purpose. Every sentence adds value: first states what it does, second explains default and optional parameter. No wasted 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 tool is simple with one optional parameter and no output schema. The description covers core functionality and default behavior. It could mention error handling or return format details, but given the tool's simplicity and sibling context, it is mostly 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?

Input schema has one optional parameter 'doc' with description listing options. Schema coverage is 100%. The description adds only the default value ('overview'), which provides marginal additional meaning 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 clearly states the tool's verb (Get) and resource (Rebillia API documentation as markdown). It explains the default behavior (returns overview) and the purpose (so Claude can read base URLs, auth, etc. without external fetches). This distinguishes it from sibling tools that are all operational data retrieval/manipulation 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?

The description implicitly tells when to use this tool: when you need API documentation, especially the overview for base URLs, auth, etc. It also explains the default and optional doc parameter. However, it does not explicitly state when not to use it or list alternatives, but there are no alternative documentation tools among 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?

With no annotations provided, the description carries the full burden. It discloses the HTTP method (GET) which implies read-only behavior, but does not mention error handling, authorization needs, or rate limits. For a simple get operation, it is minimally adequate.

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 at two short sentences, front-loaded with the core action, and contains no unnecessary 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?

Given the low complexity (one parameter, no output schema, simple retrieval), the description is complete enough to inform an agent about the tool's basic functionality.

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 provides 100% coverage with a description for billRunId. The tool description adds no additional meaning beyond what the schema already provides, so it meets the baseline but adds no extra value.

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 'Get a bill run by ID', specifying the verb (get), resource (bill run), and identifier (by ID). It effectively distinguishes from siblings like list_bill_runs or get_bill_run_invoices.

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 usage when you have a billRunId and need the full bill run object, but it provides no explicit guidance on when to use this tool over alternatives or when not to use it. Sibling tools exist but are not 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?

No annotations are present, so the description carries full burden. It mentions pagination behavior ('Returns paginated invoices') but does not disclose other traits such as error handling, rate limits, or data volume implications.

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 concise with two sentences plus the endpoint, directly stating the purpose and pagination details. No unnecessary 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?

For a simple paginated list tool without an output schema, the description covers the core functionality. However, it does not describe the return structure or fields of the invoices, which would be helpful for an agent.

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 100% coverage with descriptions, so the baseline is 3. The description adds minimal extra value by restating the optional pagination parameters, which are already in 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 clearly states the action ('Get invoices') and the resource ('for a bill run'), with the endpoint pattern. It is specific and distinct from sibling tools like get_bill_run or list_invoices.

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 lacks any guidance on when to use this tool versus alternatives like list_invoices or get_invoice. No explicit context or exclusion criteria 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?

No annotations provided, so description carries burden. Discloses auth requirement (X-AUTH-TOKEN), gateway-agnostic nature, and customerId requirement nuance. Does not describe return format or side effects, but for a read-like operation this is sufficient.

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

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

Four sentences with no wasted words. Front-loaded with purpose and usage, then details. Efficiently conveys all necessary 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 no output schema, description explains the token's purpose and usage flow. Mentions auth requirement. Lacks explicit return format or error handling, but is adequate for a simple token retrieval 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?

Input schema has 100% coverage and already describes both parameters. Description adds minimal extra context (e.g., 'for vault') that is already implied. Baseline score of 3 due to 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?

Description clearly states verb 'get', resource 'gateway client credential', and its purpose to initialize payment integration and produce a paymentMethodNonce. Distinguishes from sibling tools like create_customer_payment_method by describing the token as a prerequisite.

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?

Explicitly instructs to use returned value in hosted payment UI then pass as paymentMethodNonce to create_customer_payment_method, indicating when to use. Also notes gateway-agnostic and customerId scoping. Lacks explicit when-not-to-use 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?

No annotations provided. Description only mentions it's a GET request, implying read-only, but does not disclose error handling, authentication needs, or what happens if the currency ID is invalid.

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?

Very concise: one sentence plus HTTP path. Efficient but could be slightly more informative without being verbose.

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

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

No output schema and description does not explain what is returned (e.g., full currency object or fields). Lacks completeness for a tool with no 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?

Input schema has 100% description coverage for the single parameter. Description adds no extra meaning beyond the schema, so baseline score 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?

Clearly states the tool retrieves a company currency by ID, and includes the HTTP method and path. Distinguishes from siblings like create_currency, list_currencies, and get_default_currency.

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 alternatives like list_currencies or get_default_currency. Does not specify prerequisites or typical use cases.

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

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

No annotations are present, so the description bears the burden of behavioral disclosure. It mentions the optional include parameter and its values, which is helpful. However, it does not disclose any side effects, permissions, rate limits, or behavior on missing customer.

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, clear sentence followed by a terse list of includes. It is front-loaded with the core purpose and wastes no 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?

Given the complexity (simple get) and absence of output schema, the description is adequate but lacks details on return format, error handling, or pagination. Sibling tools with similar patterns might need more context for an AI agent.

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?

Input schema has 100% description coverage for both parameters. The description adds value by explicitly listing the possible include values (addressbook, paymentmethod, etc.), which enhances understanding beyond 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 clearly states the verb (Get), resource (customer), and identifier (by ID). It also includes the HTTP method and path for additional clarity. This distinguishes it from other get_* 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?

The description does not provide explicit guidance on when to use this tool vs alternatives like list_customers or other get_* tools. It implies usage for fetching a specific customer but lacks when-not-to-use or mention of performance considerations.

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

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

No annotations are provided, so the description must convey behavioral traits. It only states 'Get' (a read operation) and the HTTP path, but lacks details on authentication, error handling, or side effects. For a simple get, this is minimal transparency.

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 plus the HTTP path, no wasted words, and the most important information (what it does) 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?

The description adequately explains the tool's purpose and parameters, but lacks information on return values or error cases, which would be helpful since there is no 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?

Schema coverage is 100% with both parameters having descriptions, though they are basic. The description adds the HTTP path which clarifies the parameter roles. Overall, it adds moderate value beyond 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 clearly states the action (Get) and the resource (single address book entry by ID), and distinguishes from sibling tools like create_customer_address and list_customer_addresses by specifying 'by ID' and including the HTTP path with specific IDs.

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 use when retrieving a specific address entry by IDs, but does not provide explicit guidance on when to use vs alternatives, nor mentions any exclusions or 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?

No annotations provided, so description must carry behavioral disclosure. It states 'GET' which implies read-only, but does not explicitly confirm safety, idempotency, or mention any side effects. Also missing auth requirements 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?

Two sentences: first states purpose, second lists supported features. No filler, fully front-loaded, and every sentence adds 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?

Input parameters are fully covered, but output is not described. No mention of return format (list of invoices?), pagination metadata, or ordering. With no output schema, the description should compensate.

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 100%, so baseline is 3. The description summarizes parameters (pagination, include, status, dates, subscriptionId) and enumerates status values, but adds limited new insight beyond the schema descriptions. It repeats the schema's parameter descriptions.

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 'List invoices for a customer' with specific verb and resource. The HTTP endpoint GET /customers/{customerId}/invoices is provided, and the name itself differentiates from sibling tools like list_invoices or get_invoice.

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 does not explicitly compare to alternatives to help choose this tool over siblings like list_invoices, get_customer_unpaid_invoices, or get_subscription_invoices. Usage is implied by the customerId parameter but no 'when to use' or 'when not to use' 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?

With no annotations, the description alone must disclose behavior. It mentions pagination ('Returns paginated log entries') but fails to detail other relevant aspects like authentication, rate limits, or the structure of log entries. The description 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 very concise: two sentences that front-load the purpose and include the REST endpoint. Every sentence adds value without 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?

Given no output schema, the description should elaborate on return values. It only mentions 'paginated log entries', leaving the structure ambiguous. For a simple list tool, this is acceptable but not fully 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?

Schema coverage is 100%, so the description does not need to add much. However, it provides no additional meaning beyond the schema's parameter descriptions, e.g., explaining how pageNo or itemPerPage affect pagination.

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 lists activity logs for a customer, using a specific verb ('List') and resource ('activity logs'). It distinguishes from sibling tools like get_customer and get_subscription_logs by specifying the customer context and the log focus.

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 usage for listing customer logs but does not explicitly state when to use this tool versus alternatives (e.g., get_subscription_logs for subscription logs). No exclusions or context on when not to use it 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?

No annotations are provided, so the description should cover behavioral traits. It only states 'Get' and the endpoint, lacking details on security, error handling, or side effects. This is minimal disclosure for a read operation.

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

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

The description is extremely concise, with two short sentences. The key information ('Get a single payment method by ID') is front-loaded, and the endpoint is provided as supplementary detail.

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 simple nature (2 required params, no output schema, no nested objects), the description is adequate but minimal. It lacks details on return values, error handling, or prerequisites, which would be beneficial.

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 100% description coverage, so the schema already documents the two required parameters. The description adds no additional meaning or context beyond restating the parameter names.

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 verb 'Get' and the resource 'single payment method by ID', distinguishing it from sibling tools like 'list_customer_payment_methods' and 'create_customer_payment_method'. The inclusion of the full HTTP endpoint further clarifies the action.

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 usage for retrieving a specific payment method by ID, but does not explicitly state when to use it versus alternatives like listing all payment methods or when not to use it. No exclusions or context 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?

No annotations are present, so the description must disclose behavioral traits. It mentions support for pagination and include parameters, which is good, but it does not discuss response format, error handling, or potential side effects. As a read-only GET, it is safe, yet transparency could be better.

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: two sentences that convey the core purpose, HTTP method, path, and key features (pagination, include). No unnecessary 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?

Given the absence of an output schema and annotations, the description covers the essential aspects: what it does, how to use it (via path and parameters), and special features. It could mention that the response is an array or that no filters beyond customer ID are available, but it is mostly complete for a simple list 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?

The input schema already has 100% coverage with descriptions for all parameters. The description adds value by providing example values for the 'include' parameter (rateplan, rateplanCharge), which clarifies usage beyond the schema's comma-separated note.

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 verb ('List') and resource ('subscriptions for a customer'), and includes the HTTP path for clarity. It distinguishes from siblings like 'list_subscriptions' which lists all subscriptions.

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 does not explicitly state when to use this tool versus alternatives (e.g., 'list_subscriptions' for all subscriptions). Usage is implied by the name and context, but no exclusions or when-not-to-use 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?

No annotations are provided, so the description must fully disclose behavior. It mentions pagination but does not state that the operation is read-only, what data is returned, or any authorization requirements, 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 consists of two short sentences: the first clearly states the purpose, and the second adds the endpoint and pagination support. Every word adds value, and the key information 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?

For a simple list operation, the description adequately covers the purpose, resource, and pagination. While an output schema is absent, the return type (list of invoices) is implied. Could benefit from mentioning sorting or filter capabilities, but not essential.

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 100%, so the baseline is 3. The description adds nothing beyond what the parameter descriptions already provide ('pageNo, itemPerPage'), repeating the pagination concept without new semantic value.

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 verb 'List' and the resource 'unpaid invoices for a customer', distinguishing it from sibling tools like get_customer_invoices or list_invoices by specifying 'unpaid'.

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 implicitly indicates when to use (when needing unpaid invoices) but does not explicitly contrast with alternatives like get_customer_invoices or list_invoices, leaving the agent without clear 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?

No annotations provided, so description carries full burden. It implies a read-only GET request, which is accurate. However, it doesn't disclose specific behaviors like idempotency, rate limits, or any side effects.

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 (two sentences) with no wasted words. It immediately states the purpose and includes the REST endpoint, which is helpful for an agent.

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 simplicity (no parameters, no output schema), the description is nearly complete. It could mention that the default currency is a single currency object, but it's adequate for a trivial read operation.

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 zero parameters, so the description adds no param info. Per scoring rules, 0 parameters baseline is 4. The description adequately covers the trivial parameter case.

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 ('Get') and the resource ('company default currency'). It distinguishes from sibling tools like 'get_currency' (specific currency) and 'list_currencies' (all currencies).

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 includes the HTTP method and endpoint, which hints at usage, but lacks explicit guidance on when to use it versus alternatives like 'set_default_currency' or 'get_currency'. No when-not or exclusions 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?

No annotations provided, so description carries burden. It discloses HTTP method GET and numeric ID requirement, but lacks details on rate limits, authentication, error handling, or return value format.

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

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

Two concise sentences with purpose first, then endpoint and constraint. No redundant information; every word adds 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 simple retrieval tool with no output schema, the description does not explain what is returned (e.g., product details). It mentions the endpoint but not the response structure, leaving the agent with incomplete information.

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 100% with parameter descriptions already present. The description repeats the numeric requirement for externalProductId but adds no new semantic meaning beyond 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 clearly states 'Get an external product by ID' with specific verb and resource. It includes the REST endpoint and a requirement that productId is numeric, distinguishing it from sibling tools like list_external_products.

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 usage for retrieving a single product by ID but does not explicitly state when to use it versus alternatives like list_external_products or link_external_product. No guidance on when not to use it.

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

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

No annotations are provided, so the description carries the full burden. It only states the HTTP method and operation. It does not disclose potential side effects (none expected), required permissions, error conditions, or return value structure. This is minimal and leaves the agent with little behavioral context beyond the schema.

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

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

The description consists of two short sentences that immediately convey the action and the REST endpoint. Every word is functional; there is no wasted text. It is perfectly concise for a simple retrieval.

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 simplicity (one required parameter, no output schema, no nested objects), the description provides the essential information. However, it could be slightly more complete by briefly describing what a gateway is or that it returns a full gateway object. It is not incomplete, but there is room for improvement.

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 100%, with the single parameter gatewayId described in the schema. The description does not add any additional meaning beyond what the schema already provides, so a baseline score of 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 clearly states 'Get a company gateway by ID', which is a specific verb-resource combination. It distinguishes from sibling tools like list_gateways, create_gateway, delete_gateway, and update_gateway by specifying retrieval by ID.

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

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

No explicit when-to-use or when-not-to-use guidance is provided. However, as a basic retrieval tool, the usage context is implied by its name and description. It does not mention alternatives or exclusions, so it is adequate but not directive.

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

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

No annotations provided; description only states it's a GET request (implying read-only) but lacks details on side effects, authentication requirements, rate limits, or error handling. The return format is not described.

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?

Description is brief (two sentences plus a list) and front-loaded with the core purpose. The list of keys is redundant with the schema but acceptable.

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 one parameter and no output schema, the description fails to explain what 'global integration info' entails or indicate response format, error conditions, or usage hints.

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

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

Schema description coverage is 100%, and the parameter's description already lists all valid values. The description repeats this list and adds the endpoint, but adds no new meaning beyond 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 explicitly states 'Get global integration info by key name', clearly defining the action and resource. It distinguishes from siblings like list_integrations by specifying a single key lookup.

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 lists valid key names but provides no guidance on when to use this tool vs alternatives (e.g., list_integrations, get_integration_config). No when-not-to-use or 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?

No annotations are provided, so the description carries the full burden. It only states 'get config' without disclosing behavioral traits like authentication needs, rate limits, or what the config contains. This is minimal transparency.

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 plus the endpoint, with no wasted words. It is concise but lacks structure; however, for such a simple tool, this is 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 simple tool with one parameter and no output schema, the description is adequate but incomplete. It does not explain the response structure or any side effects, which would be helpful for an AI agent.

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 100% with a clear description for integrationId. The description adds no additional meaning beyond the schema, so 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 clearly states 'Get company integration config by ID' with a specific verb and resource. It also provides the HTTP endpoint pattern, uniquely identifying the tool among siblings like get_integration_by_key.

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 does not provide explicit guidance on when to use this tool versus alternatives (e.g., get_integration_by_key). Usage is implied but no exclusions or context 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?

No annotations are provided, so the description must convey behavioral traits. It mentions GET method implying read-only, but fails to disclose error handling, rate limits, or other side effects. This is insufficient for a zero-annotation scenario.

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, clear sentence front-loaded with the action and resource. Every word serves a purpose, making it highly 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?

Given no output schema and few parameters, the description adequately covers the tool's primary purpose. However, it lacks behavioral details (e.g., read-only nature) that would be expected without annotations. Slightly incomplete for a simple retrieval 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 100%, with both parameters already documented. The description adds 'Optional: include' but no additional meaning 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 clearly states the action (Get), resource (invoice), and method (GET /invoices/{invoiceId}). It distinguishes from sibling tools like list_invoices, create_invoice, delete_invoice, etc., by specifying retrieval by ID.

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 usage when an invoice ID is known, but does not explicitly state when to use this tool versus alternatives like list_invoices or get_customer_invoices. No when-not 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?

Specifies HTTP GET, implying read-only operation. No annotations present, so description carries burden. Lacks details on error handling, authentication, or rate limits, which are common for a retrieval tool.

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

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

Extremely concise: three distinct pieces of information (purpose, endpoint, optional parameter) in one sentence, no filler 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?

For a simple get tool with no output schema, description omits return value details and common error scenarios. While adequate for basic use, more completeness would improve agent effectiveness.

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?

Adds context beyond schema by indicating productId is a path parameter ('GET /products/{productId}') and that include is optional. Schema already covers both parameters with descriptions, so extra value is moderate but helpful.

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?

Clearly states 'Get a product by ID' with specific verb and resource. Includes HTTP method and path for clarity. Distinguishes from sibling list/get tools by focusing on single product retrieval by ID.

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?

Description implies usage when you have a product ID, but does not explicitly contrast with list_products or other getters. No when-not-to-use 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?

Without annotations, the description carries full burden. It correctly identifies the HTTP method as GET, implying a read-only operation. However, it does not disclose authentication requirements, rate limits, or any error conditions. The description is minimal but sufficient for a simple retrieval.

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

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

Two sentences with minimal waste. However, the URI is repeated twice redundantly. Could be slightly more concise by stating it once.

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 get-by-ID tool, the description covers the basic action but lacks expectations about the response structure, pagination, or sorting. No output schema exists, so more context on return values would be beneficial.

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 100%, so baseline is 3. The description adds no new meaning beyond the schema; it repeats the ratePlanId URI pattern which is already in the schema. The optional include parameter is not elaborated.

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 'Get a rate plan by ID', using a specific verb and resource. It distinguishes from sibling tools like list_product_rate_plans (listing) and create_product_rate_plan (creation).

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 alternatives. It does not specify any prerequisites, when to use list vs get, or mention the optional include parameter's purpose. The context is purely implicit.

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