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

Annotations already disclose this is a non-read-only, non-idempotent mutation, and the description reinforces that with 'Allowed once,' adding a hard business precondition (before first payment) and error behavior ('fails with the app's own sentence'). It does not describe permissions or the return payload, but coverage of behavior beyond the annotations is solid.

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, front-loaded with the action and benefit, followed by the constraint. No filler. The 'fails with the app's own sentence' phrasing is slightly vague but earns its place by signaling error surfacing.

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 single-parameter mutation with annotations and no output schema, the description covers purpose, effect, precondition, and failure mode. Only the parameter format and the exact failure surface are left thin, which is a minor gap at this complexity level.

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 0% for the single 'code' parameter, so the description carries the burden, yet it only gestures at meaning via 'the owner of a referral code' and gives no format, length, or validation hints (schema imposes 3-40 chars). Adequate but incomplete compensation for the coverage gap.

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 ('Record') and resource ('referred by the owner of a referral code') and clarifies the downstream effect (discount plus friend's credit). It implicitly distinguishes itself from the sibling set_referral_code (recording someone else's code vs. setting your own), but never names the sibling 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?

States a clear precondition and exclusion: 'Allowed once, before the first payment; fails ... otherwise.' This tells the agent when the call will succeed and when it won't. It stops short of naming an alternative tool or recovery path when the precondition fails.

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