pay_and_call

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 of behavioral transparency. It discloses that broadcast is not executed and that it returns the target for the host to send, which is useful, but it does not mention that 'tool' must be a valid tool name, how verification happens, or failure modes. The statement 'this returns the target so a host calling the server can send via the SDK wallet' is somewhat opaque.

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 moderately concise but has an awkward structure with parentheticals and 'Agent side' context. It front-loads the main action but includes caveats that might be better placed elsewhere. It is not overly verbose but could be clearer.

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 (3 params, no output schema, no annotations), the description is incomplete. It fails to specify parameter formats, valid tool names, exact return structure, and error handling. The caveat about broadcast is important but not enough to make the tool callable correctly without more 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?

Schema description coverage is 0%, and the description provides no explanations for the parameters (request_id, amount_raw, tool). It does not clarify that amount_raw is in raw units, what format request_id should be, or what tool names are accepted. The description is insufficient for an agent to construct valid arguments.

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 states the action: 'pay its one-time address and call `tool` after verify.' It names the resource (request_id) and the operation (pay and call), but is somewhat convoluted. It does not clearly distinguish from siblings like verify_payment or get_address, and the mention of 'Agent side' is unusual.

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 alternatives are given. The caveat about broadcast not executed in tests is a helpful context note, but it does not guide the agent on when to choose this tool over others. Siblings like verify_payment 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.