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

Richly exceeds the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=true, destructiveHint=false). It discloses billing behavior (debits the add-on, 30-day window, no double charge), idempotent replay semantics, that delivery truth lives in the attempt record and not registration, URL validation (loopback/private/metadata refused), one-time secret exposure, and refund-on-refusal. This is exactly the extra context annotations cannot carry.

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 a dense wall of text that leads with payment boilerplate before the actual purpose, and repeats 'after paying, poll /v1/resolutions/:id until horizon_end' verbatim twice. Substantive content is present, but significant redundancy and poor front-loading hurt efficiency.

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?

With an output schema present, return values need not be explained, and the description still covers payment rails, refunds, validation behavior, secret handling, and the post-registration polling step. An agent has everything required to invoke and sequence this tool correctly.

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 0%, so the description must compensate: it defines `url` as a public http(s) URL validated at registration and explains `payer` (Base 0x… address) plus alternative transport via the x-tollbridge-payer header or PAYMENT-SIGNATURE. Both parameters gain meaning beyond the raw schema, though exact URL constraints are only loosely specified.

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+resource: 'register an outcome hook endpoint: a public http(s) URL that Tollbridge POSTs to when one of the payer's decisions settles (realized or unresolvable).' No sibling competes (it's the only hook tool), and the trigger condition is named. However, the purpose is buried behind leading payment-protocol boilerplate, weakening the front-loading of the purpose statement.

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?

Gives workflow guidance ('after paying, poll /v1/resolutions/:id until horizon_end') and idempotency context (re-registering inside the window replays honestly), which implies when registration matters. But it never contrasts this tool against alternatives and leaves the register-then-poll relationship implicit rather than as explicit when/when-not guidance.

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