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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=true, but the description explains *why* idempotency matters (duplicate calls would double-pay the referrer) and that the same identifier must be reused on refund. It adds the campaignId default-to-env-var fallback, which annotations do not convey. It says nothing about auth/permission requirements or rate limits.

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 action and then the critical identifier requirement before the targeting detail. The enumeration of seven identifier names restates the schema's anyOf and is the only mildly wasteful element.

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?

An output schema exists, so return values need not be described, and annotations cover the safety profile. Still, for a 28-parameter mutation tool with nested anyOf/if-then constraints, the description omits the meaning of the amount and invoice fields and the paymentProvider/testMode interaction that the schema only partially documents.

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 only 11% across 28 parameters, so the description carries real weight and does explain the dedup-key concept plus the campaignId fallback. However, it leaves the large family of financial fields (grossAmount vs netAmount vs amountPaid vs amountCashNet, invoice totals, tax arrays, paidAt, subscriptionId, customerId) entirely unexplained, which is a significant gap for a money-handling tool.

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 states a specific verb and resource ('Record a sale/transaction for an affiliate program'), which is clear enough to distinguish it from the CRUD-oriented campaign/reward siblings. It also hints at the adjacent refund flow ('reuse the same one when refunding'), but never explicitly names a sibling tool, so it stops short of full differentiation.

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 gives real operational context: use webhooks rather than polling to learn when commissions land, and always supply a transaction identifier so repeats de-duplicate instead of double-paying. It does not state when to prefer this tool over alternatives such as trigger_referral or add_participant, so no explicit exclusions are provided.

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