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

Annotations already declare destructive=true, idempotent=true, openWorld=true and readOnly=false, so the safety profile is covered; the description adds real value beyond that by disclosing the concrete consequence (unlocking the referrer's rewards and triggering reward emails/texts) and the pre-condition that produces an error. It stops short of 5 because it doesn't explain whether a failed or repeated confirm is safe, despite the idempotent hint.

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 tight sentences, front-loaded with the "WRITE:" marker, then the condition, then the side effects and identification strategy, then endpoints. No sentence is filler and the most decision-relevant information comes first.

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 eight parameters, no output schema and a 100%-documented input schema, the description covers the precondition, side effects, identification approach and error behavior, which is what an agent needs to call it correctly. The only remaining gap is guidance on choosing between this and the sibling qualify/unqualify operations.

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 already 100%, so a baseline 3 applies; the description earns a bump by explaining that the referral is identified either by subscriber_id or by the campaign's unique identifier, which frames the email/phone/wallet/custom-identifier alternatives in the schema as mutually exclusive lookup modes rather than independent fields. It still doesn't clarify precedence if multiple identifiers are supplied.

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 gives a specific verb and resource ("confirm a verified referral") plus the exact gating condition (third conversion event) and the HTTP endpoints, so the operation is unmistakable. It falls short of a 5 because it never names or contrasts with adjacent siblings such as qualify_referral or unqualify_referral, which an agent may easily confuse with confirming.

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?

It states clearly when to call it (campaign goal tracks three events, third event has occurred) and that the API errors otherwise, which is actionable positive and negative guidance. It does not name an alternative tool or say when to prefer qualify_referral instead, so exclusion-based routing is left to inference.

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