Ghana Payments (Paystack — MTN MoMo)

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds that cancellation prevents renewal and that email_token is auto-resolved. However, it does not disclose potential side effects (e.g., impact on billing, reversibility) or success/failure behavior. Overall adequate but not comprehensive.

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 concise sentences with no redundant words. It is front-loaded with the core purpose and includes essential parameter guidance efficiently.

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

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

For a tool with two parameters, high schema coverage, and no output schema, the description covers purpose and parameter usage sufficiently. However, it lacks an explanation of the return value or expected outcome after cancellation, which would enhance 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%, so the description adds limited value. It reiterates the source of subscription_code and the optionality of email_token, which is already in the schema. No additional constraints or usage hints are provided 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 'Cancel' and resource 'subscription', and specifies the effect 'so it will not renew'. It also mentions the required parameter 'subscription_code' from 'query_subscription', distinguishing this tool from siblings like 'create_subscription_link' or 'query_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 tells the agent to pass the 'subscription_code' from 'query_subscription' and notes that 'email_token' is optional and auto-resolved. This provides clear context for usage, though it does not explicitly state when to use this tool versus alternatives or 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?

Provides detailed behavioral context: returns a hosted checkout URL, payment completes automatically, no confirm step. Clarifies credentials via header, and that money flows buyer->Paystack->merchant. Adds significant value beyond annotations.

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

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

Description is informative and front-loaded with key details. Slightly verbose with explanatory sentences about money flow and credentials, but each sentence adds necessary context.

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

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

Given no output schema, the description explains the return value (hosted checkout URL). Covers authentication, payment flow, and limitations. Sufficient for an agent to use the tool correctly.

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

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

Schema coverage is 100%, but the description adds extra constraints: 'decimals allowed' for amount, character limits for description and reference_id, and notes about optional success_url. This 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?

Clearly states it creates a payment link in GHS for Ghana via Paystack, with specific verb and resource. Distinguishes from the sibling tool query_payment_status which is a query operation.

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?

Describes when to use: to create payment links for Ghana via Paystack. Explains the payment flow and that no confirmation step is needed. However, it does not explicitly mention when not to use or compare with the sibling.

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

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

Annotations indicate readOnlyHint=false and openWorldHint=true. The description adds that amounts are checked before creation and policy guardrails apply, providing extra context without contradicting annotations.

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

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

The description is two sentences, front-loaded with the main purpose, and covers all key aspects efficiently. 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 description provides sufficient context for a tool with no output schema, implying the return is a URL. It covers billing, buyer flow, and validation. Slight gap: explicit return type not stated, but implied.

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 by clarifying 'Amount is per billing period', describing description as 'plan name, <=80 chars', and noting default interval. It enhances understanding without being redundant.

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 recurring subscription checkout link' and specifies billing details (GHS, monthly/yearly/weekly). It distinguishes from siblings like create_payment_link by highlighting recurrence.

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

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

The description explains when to use the tool (for recurring subscriptions) and mentions policy guardrails. However, it does not explicitly state when not to use it or compare with alternatives beyond 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?

Annotations provide readOnlyHint and openWorldHint. Description adds that it queries Paystack directly (pull-based) and that 'paid=true when status is PAID'. It does not disclose error behavior or response structure beyond the paid boolean hint. Given annotation coverage, additional behavioral context 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 two concise sentences with no filler. Purpose is front-loaded. 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?

For a simple single-parameter tool with annotations, the description covers the core purpose, mechanism, and output interpretation. It lacks details on errors or invalid references, but is largely complete given 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% and the parameter 'reference' is well-described in the schema as 'The reference returned by create_payment_link'. The description adds no new detail about the parameter beyond tying it to the creation tool.

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 the tool checks whether a Ghana payment (created by create_payment_link) has been paid, using a direct pull-based query to Paystack. It clearly distinguishes from the sibling create_payment_link by focusing on status checking.

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 indicates when to use the tool (to check payment status) and highlights the pull-based mechanism with no need for webhooks. It does not explicitly state when not to use it, but the single sibling (create_payment_link) is clearly different in purpose.

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

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

The description aligns with annotations (readOnlyHint=true) and adds value by disclosing possible status values (ACTIVE, NOT_SUBSCRIBED_YET) and explaining that the result includes subscription_code and email_token for future use, which annotations do not cover.

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 purpose, then elaborates on return values. Every sentence is necessary and efficient.

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

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

For a simple tool with one parameter and no output schema, the description covers purpose, usage, key return fields, and hints at next steps. Minor omissions like error handling are acceptable given 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% for the single parameter 'reference', and the description simply restates the schema's description without adding new semantic detail. 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 the verb 'Check' and the resource 'subscription', and specifies the unique context of using the reference from create_subscription_link, effectively distinguishing it from sibling tools like query_payment_status.

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

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

The description provides contextual guidance on interpreting the 'active' field and mentions keeping subscription_code and email_token for cancellation. However, it lacks explicit when-not-to-use instructions or comparisons with alternatives.

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

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

Annotations already indicate destructiveHint=true, and the description adds valuable context: it specifies the guardrails check before gateway processing. No contradictions with annotations. However, it does not disclose potential failure modes or side effects beyond the guardrails.

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 purpose, every sentence adds value. 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?

No output schema exists, and the description does not mention what the tool returns (e.g., success indication, refund object, error handling). The agent lacks information about expected response or side effects beyond the guardrails check.

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, but the description clarifies the amount parameter with 'Full refund by default; pass amount for a partial refund where supported' and links the reference to query_payment_status. This adds meaning beyond the schema's property 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 it refunds a paid payment created by create_payment_link, distinguishing it from sibling tools (create_payment_link, query_payment_status). The verb 'refund' and resource 'paid payment' are specific, and the scope is well-defined.

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

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

The description explains default behavior (full refund), optional partial refund, and mentions guardrails (x-agentpay-max-amount). It provides context for when to use partial refunds, but lacks explicit exclusion criteria (e.g., 'do not use if payment is unpaid') or a direct statement of alternatives.

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