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

Goes well beyond the annotations (readOnlyHint/destructiveHint=false only cover the safety profile): it discloses the long-poll timeout behavior via wait_seconds, the complete status enumeration including failure states, that a single-use `card` locked to the purchase is returned on approval, and that the first approval yields a `connect_token` to be persisted and sent as a Bearer on all future calls. This is exactly the kind of auth and lifecycle context an agent needs to drive the flow correctly.

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?

Front-loads the core purpose and the status list, then the claim-specific and connect_token instructions. Content is dense and mostly earns its place, though the status enumeration and the connect_token instructions sit in separate paragraphs that could be tightened slightly.

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 no output schema, the description must explain returns, and it does: it enumerates every possible status value and calls out the conditional `card` and `connect_token` fields. Combined with the polling-loop guidance and auth instruction, an agent has everything needed to call and interpret this tool.

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 0%, so the description carries the full burden and does: charge_id is identified as the 'clm_…' poll_id from request_payment for claims, agent_secret is explained as the secret received for a claim, and wait_seconds is tied to the long-poll duration. All three parameters gain meaning not present in the bare schema.

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 ('Poll for the outcome of a payment request') and immediately names the result states, making it unmistakable against siblings like request_payment. An agent can tell this is the read-side counterpart to request_payment without opening either schema.

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?

Explicitly says to call again while the status is pending/claim_pending and references the upstream sibling by name ('the clm_… poll_id from request_payment'), which gives the agent a clear routing context. It stops short of stating when not to use it or naming alternative siblings, so it is strong but not a full when/when-not/alternatives statement.

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