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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds a genuinely non-obvious behavioral fact: the api_key is returned exactly once, which explains the idempotentHint=false and warns the agent that a missed response cannot be recovered. It stops short of describing the unpaid/pending response.

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; the source tool is named first and the success return is front-loaded.

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?

There is no output schema, no annotation coverage of the pending-state behavior, and no parameter documentation, so the description is only marginally sufficient for a polling tool whose contract (what comes back when unpaid, whether retries are safe) matters for correct invocation.

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% for two required parameters, so the description must carry the meaning of session_id and claim_token – yet it mentions neither. The exactly-once return implies the claim_token is single-use, but the agent must infer that rather than read it.

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 ('Poll') and resource ('a purchase'), names the sibling that produces the purchase (buy_credits), and says what is returned on success. An agent can distinguish this from buy_credits 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?

Usage is implied by 'Poll a purchase from buy_credits' – call it after starting a purchase – but there is no explicit guidance on polling cadence, when to stop, or what to do while the purchase is unpaid.

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