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

Goes well beyond the annotations: one inviter per organization, immutable attribution, self-invitations refused, ALREADY_APPLIED retry semantics, bonus granted without starting a campaign, and a different invitation cannot replace an existing one. The retry-safe description sits in mild tension with idempotentHint=false, but the annotation's effect-based meaning (a second call with a different code is refused) is not directly contradicted.

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-loaded with the action and timing constraint, and every subsequent sentence carries a distinct behavioral fact (immutability, retry behavior, recovery). It is dense and semicolon-heavy, but there is no filler to remove.

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 one-parameter irreversible mutation with no output schema, the description covers the eligibility window, the idempotent retry outcome, the ALREADY_APPLIED signal, the side effect (traffic welcome bonus, no campaign), and the state-recovery tool. An agent has enough to call it and to handle an ambiguous result.

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 100% and there is only one parameter, so the schema already carries the syntax and length constraints. The description reinforces that the value must be developer-supplied and used before first publication, but adds no format or URL-parsing detail beyond the 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 (apply) and resource (referral code or invitation URL) and names the exact target (this organization before its first-ever Sandbox publication). It is clearly distinguishable from the sibling get_referral_program, which is presented as the read-side counterpart.

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?

Gives explicit preconditions ('before its first-ever Sandbox publication'), an explicit prohibition ('Never invent a code'), and an explicit recovery path ('Read get_referral_program to recover state after an uncertain result'). The when-to-use and the alternative for the failure case are both stated rather than implied.

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