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

With no annotations, the description carries the full burden and does well: it enumerates the three outcome states and their payloads (a single-use credential, a hold_id while a human is asked, or a block reason), disclosing the human-in-the-loop flow. It also explains idempotency semantics for retries. It omits what happens after pending_human/blocked and any permission or side-effect context.

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?

Two tight sentences with zero filler, and the outcome semantics are front-loaded. Every clause carries information an agent needs, and there is no redundant restatement of the schema.

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 10-parameter, high-stakes mutation tool with no annotations and no output schema, the description usefully covers return states. However, it leaves the follow-up flow unclear: what an agent should do with a hold_id for pending_human, and how the returned single-use credential relates to the sibling pink.get_credential.

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 90%, so the schema already documents nearly every parameter in detail, including the exact idempotency_key behavior. The description's only parameter-level addition, "Pass idempotency_key to make retries safe," repeats what the schema field already states more precisely, so baseline 3 is appropriate.

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 opens with "The real call," which implicitly contrasts with the dry-run sibling pink.check_policy and, combined with the outcome states (allowed/pending_human/blocked), makes clear this is the tool that actually submits a payment. It never restates the verb+resource itself, leaning on the name and title, but an agent can still distinguish it from check_policy. Clear purpose without fully self-contained phrasing.

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?

Usage is only implied through "The real call" versus the check_policy dry run, and the note to pass idempotency_key for safe retries. There is no explicit statement of when to call this versus pink.check_policy or pink.get_credential, and no prerequisites or exclusions are given.

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