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

With no annotations, the description carries the full burden and does so unusually well: it discloses the paid cost and protocol, that invalid input is rejected before any charge, the three-valued outcome with attached evidence and receipt, and replay semantics tied to idempotency_key. Cost, failure mode, and retry behavior are exactly the facts an agent cannot infer from the schema.

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?

Four tight sentences, front-loaded with the paid-check framing, then output, then error and retry behavior. The parenthetical price and protocol are compressed efficiently; no sentence is filler.

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 description covers purpose, outputs, charging, and retry, which is strong for a paid tool with no annotations and no output schema. But with 6 required parameters at 13% schema coverage, an agent still cannot tell what a valid network/asset/requested_at value looks like or how counterparty_id interacts with recipient_address.

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 13% across 8 parameters, so the description must compensate and largely does not: recipient_address, network, asset, requested_at, purpose, and counterparty_id get no meaning at all. Only idempotency_key gains real semantics (reuse on uncertain outcome; replay returns the stored receipt), which is valuable but covers one of eight fields.

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?

States a specific verb and resource: a pre-signing safety check of a planned payment, and names the return vocabulary (allow/escalate/block with reasons, evidence, receipt). This is clearly distinguishable from siblings like get_receipt (which fetches a stored result rather than producing a verdict) and ping/list_capabilities.

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?

'Pre-signing' pins the moment of use precisely, and the idempotency sentence tells the agent what to do on an uncertain outcome. It stops short of explicit exclusions or naming a sibling as the alternative when a verdict already exists, so this is clear context rather than full routing guidance.

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