pay_invoice

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

The description discloses important behavior not in annotations: that v1 returns a deep link instead of doing headless payment, and that confirm=true is required. This is valuable. However, annotations already include destructiveHint=true, and the description does not elaborate on the destructive nature (e.g., irreversible charge, need for user confirmation beyond the confirm flag). No contradiction found.

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 packed with critical details: purpose, v1 limitation, and a usage requirement. No fluff. Front-loaded with the verb and resource. Ideal for quick scanning.

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 moderate complexity (3 params, 1 required), the description covers the essential behavior (deep link return, confirm requirement) and the source for file_id. It lacks an explicit note on what the preview looks like or error conditions, but that might be acceptable with the confirm hint. Slight omission: doesn't mention prerequisites like having an active session, but that may be implied by the origin param.

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%, meaning all parameters are described in the schema. The description adds context for 'file_id' (from list_workspace_files with file_type=invoice) and 'confirm' (must be true to avoid preview), which enriches semantics. But it does not add significant detail to 'origin' beyond schema. Baseline 3 is appropriate given high 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 the tool's purpose: to pay an invoice from a vendor. It also notes the v1 behavior of returning a deep link rather than headless payment, which is a specific and useful detail. However, it does not explicitly differentiate from other payment-related siblings like 'list_payments' or 'list_payment_methods', which could be a minor distinction.

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 through the example (pay an invoice) and the mention of 'confirm:true', but it does not explicitly state when to use this tool versus alternatives, such as 'list_payments' for viewing payments or 'sign_contract' for contracts. It lacks a clear 'when not to use' or reference to sibling tools.

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