Digital Goods MoR aggregator (Paddle, Lemon Squeezy, Polar, Whop, Creem, Dodo, FastSpring, 2CO)

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

The description extensively explains behavioral differences across platforms (e.g., immediate vs period-end cancellation), credential headers, and the destructive nature of the operation. This far exceeds the annotations which only set destructiveHint true.

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 lengthy but necessarily detailed due to platform variability. It is front-loaded with the purpose and well-structured by platform. A few sentences could be tightened, but 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 tool with no output schema and high complexity (multiple platforms, different behaviors), the description is comprehensive. It covers credential setup, platform behaviors, and return value, giving the agent all needed contextual 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 description coverage is 100%, so the baseline is 3. The description adds extra context about credential headers and platform-specific behaviors for the 'immediately' parameter, enhancing 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 it cancels a subscription on merchant-of-record platforms. It lists specific platforms and their behaviors, distinguishing this cancellation tool from sibling tools like create_checkout or issue_refund.

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 clear context for when to use this tool (cancelling subscriptions) and details platform-specific behaviors. However, it does not explicitly state when not to use it or mention alternatives, though no other cancellation tool exists 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?

Discloses that the server never touches funds, describes credential setup, and notes that capabilities differ per provider. Adds context beyond annotations (e.g., money flow, owner-policy headers) without contradiction.

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

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

Dense with information but well-structured: purpose stated upfront, followed by provider details and parameter nuances. Every sentence earns its place given the complexity; slightly long but justified.

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?

Thoroughly covers all 9 parameters, provider-specific behavior, credential headers, and owner-policy setup. With no output schema, the description explicitly states the return value ('checkout_url'). Matches the complexity of the tool.

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

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

Schema coverage is 100%, but the description adds extensive provider-specific semantics for each parameter (e.g., 'item' format per provider, 'amount' custom price behavior, zero-decimal currency handling). This adds meaningful value beyond the schema alone.

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

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

Description clearly states the tool creates a hosted checkout link for digital products via a merchant-of-record platform. It specifies the verb ('create'), resource ('checkout link'), and scope ('digital product / software / course'), and distinguishes from siblings by detailing the unique function and provider flexibility.

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?

Provides explicit guidance on when to use the tool (for creating checkout links) and how to pick among eight providers with detailed parameter notes. Lacks explicit 'when not to use' instructions but sibling context implies clear boundaries.

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 destructiveHint=true and readOnlyHint=false. The description adds details like Paddle's pending_approval on production and the owner policy gate on amount. No contradictions with annotations.

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

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

The description is long but well-structured with provider-specific sections. It front-loads the main purpose. While not concise, the length is justified by the complexity of the tool.

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

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

Given the complexity (4 params, no output schema, destructive), the description covers credentials, environments, owner policy, and provider-specific behaviors. It does not mention the response format, but the overall completeness is high.

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 crucial provider-specific behavior for each parameter. For example, it clarifies that amount must be omitted for some providers and required for Polar. The reason field is explained per provider.

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 'Refund an order through the merchant-of-record platform.' The verb and resource are unambiguous. It distinguishes from siblings like cancel_subscription and query_order by focusing solely on refunding orders.

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 explicit when-to-use and when-not-to-use guidance per provider. It specifies which providers support partial vs full refunds, which require amount, and lists unsupported providers (Whop, Creem). This prevents misuse.

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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds significant behavioral details beyond annotations: the unified status enum, raw passthrough, and complex authentication requirements (headers for provider, key, environment). No contradictions.

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 information-dense but verbose and could be better structured (e.g., bullet points). It front-loads the purpose but includes many details about credentials that could be separate. Some redundancy with input 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?

For a query tool with multiple providers and authentication, the description covers essential aspects: purpose, parameters, return values (unified enum + raw), and credential setup. No output schema, but return format is explained. Missing error handling details, but adequate for the complexity.

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 both parameters. The description adds value by explaining the format of order_id for each provider and noting that provider can be passed via header. This goes beyond the schema definitions.

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 purpose: 'Get the status of an order / transaction'. It specifies the verb and resource, and distinguishes from sibling tools like cancel_subscription, create_checkout, etc. It provides specific details about the returned status enum.

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 clear context on when to use the tool, including supported providers, credential headers, and environment selection. However, it does not explicitly state when not to use this tool or directly mention alternative tools, though siblings are listed outside the description.

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?

Beyond annotations (readOnlyHint, idempotentHint), the description details credential headers (x-mor-provider, x-mor-key, x-mor-env) and owner-policy headers, plus the return structure (unified status enum, raw_status, raw passthrough). No contradictions with annotations.

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

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

The description is dense but contains all necessary information without fluff. It could be slightly better organized (e.g., bullet points for headers), but it's efficient and front-loaded with the core purpose.

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

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

Given the complexity (multiple platforms, credential headers, unified response), the description is complete. It covers input parameters, provider enum, ID formats, headers, and output structure. No output schema exists, so the description adequately explains return values.

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 baseline is 3, but the description adds significant value by explaining ID formats for each platform (Paddle sub_..., Lemon Squeezy numeric, etc.) and providing context for the provider parameter. This goes beyond the schema's enum 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?

Description clearly states 'Get the status of a subscription on the merchant-of-record platform', specifying the verb and resource. It lists supported platforms and ID formats, distinguishing it from sibling tools like cancel_subscription or issue_refund.

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 this tool is for querying subscription status. While it doesn't explicitly say when not to use it, the sibling tool list (cancel_subscription, create_checkout, etc.) provides context. A brief usage distinction would improve clarity.

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