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

With no annotations, the description carries the full behavioral burden. It usefully discloses the async approval flow (the credential appears only after a person approves) and that any payment_id is accepted, but it omits what is returned while still pending, whether polling is rate-limited, and any auth requirements — notable gaps for a mutation-adjacent status tool.

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?

Three short sentences, front-loaded with the core action and return behavior, and no wasted filler. The closing sentence is brief and additive rather than redundant.

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 one-parameter tool with no output schema and no annotations, the description covers the essential return value ('returns the credential') but leaves the pending/not-approved state and error behavior unexplained. Adequate but with clear gaps for an agent deciding what to do on a non-credential response.

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 100% and the single hold_id parameter is already documented as 'hold_id / payment_id returned by pink.request_payment'. The description's 'also works for any payment_id' largely restates the schema, so the baseline 3 applies with no additional format or syntax detail.

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 concrete action (check a pending payment) and the payoff (returns the credential once a person approves), which is clearer than the vague title 'Poll a hold'. It is distinguishable from pink.request_payment, the sibling that creates the hold, though the description never names that dependency explicitly.

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?

'Check a pending payment' implies the tool is used after a payment request has been made and before approval lands, but no when-to-use/when-not guidance or sibling alternatives are given. The agent must infer the polling lifecycle from the word 'pending' alone.

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