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

Annotations already indicate this is not read-only, not idempotent, and not destructive. The description adds valuable behavioral context: it never sends the payment, and it warns against retrying an uncertain signing attempt with a new nonce. This goes beyond the annotations by disclosing the non-retry rule and the non-sending behavior, which are critical for an agent to avoid double-signing or accidental payment execution.

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 with no wasted words. The core action is front-loaded, and the two most important behavioral constraints (never sends, never retry with new nonce) are stated immediately. Every sentence earns its place.

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 signing tool with 9 required parameters and no output schema, the description covers the critical behavioral constraints: exactness, non-sending, non-retry, and secret handling. It does not explain the full signing flow or what the return value looks like, but the schema covers parameter details and the description covers the operational cautions. The lack of an output schema is partially mitigated by the clear behavioral guidance.

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 89%, so the schema already documents most parameters. The description adds meaning by emphasizing 'exact' for tool, resource, and amountAtomic, and by warning that capability is a secret credential that must never be logged or persisted. It also clarifies that validAfter must be '0' and validBefore is at most 300 seconds ahead, which reinforces the schema. The description does not add much beyond the schema, but the security warning and exactness emphasis are valuable.

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 a specific verb ('Sign'), a precise resource ('one exact allowlisted Base-USDC research payment'), and a scope ('under an existing bounded capability'). It also distinguishes itself from related autopay tools by emphasizing it only signs and never sends, which is a clear differentiator among the otto_muse_autopay_* siblings.

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: use this tool to sign a single exact allowlisted payment under an existing bounded capability. It implies this is the signing step after preparation and before any send, and it warns against retrying uncertain attempts. It does not explicitly name alternatives like otto_muse_autopay_prepare or otto_muse_autopay_enroll, but the 'existing bounded capability' and 'exact allowlisted' phrasing effectively scopes when it should be used.

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