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

Annotations already indicate readOnlyHint=false (mutating) and destructiveHint=false (not destructive). The description adds behavioral details: it retrieves the invoice, runs settlement via POST /settle, and marks it PAID. It also explains sandbox vs. live mode outputs. This goes beyond annotations by clarifying the multi-step process and simulation behavior. However, it does not mention possible failure modes or side effects like fees.

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 long, with no wasted words. It front-loades the purpose, then explains the process, and finally distinguishes output by mode. Every sentence serves a clear function, making it efficient and easy to parse.

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 an output schema (external), so the description needn't detail return values. It covers the core workflow, sandbox vs. live behavior, and references the settlement endpoint. However, it could be more complete by mentioning prerequisites (e.g., invoice status) or potential failures. Given the moderate complexity (payment + settlement + on-chain), the description is sufficiently complete but not exhaustive.

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 all three parameters (invoiceId, sandbox, recipientAddress). The description adds only minimal context: it notes that sandbox mode returns a simulated receipt. It does not explain recipientAddress's conditional requirement beyond the schema's existing note. Thus, the description adds little value beyond the schema, earning 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 tool pays an agent-to-agent invoice by ID, with a specific verb ('Pay') and resource ('agent-to-agent invoice'). It outlines the steps (retrieve, settle, mark PAID) and distinguishes from sibling tools like invoice.create (create) and settlement.execute (separate settlement). This makes the purpose unambiguous and well-differentiated.

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 paying invoices by ID, but it does not explicitly state when to use it versus alternatives (e.g., settlement.execute or other payment flows). No prerequisites or post-conditions are mentioned, such as the invoice needing to exist or be in a specific state. The usage guidance is adequate but lacks explicit exclusions or comparisons.

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