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

Beyond annotations, the description reveals important behavior: the address becomes fixed at enrollment, referral terms must be accepted, and commission payout is gated on a public non-test message. This adds meaningful context and does not contradict the readOnly/destructive/idempotent hints.

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 short sentences with no filler; the lead sentence states the action and outcome, and the later sentences add only high-value constraints. The pointer to speedbot_referral_program is an efficient way to avoid duplicating payout details.

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 simple enrollment tool with no output schema, the description covers the prerequisites, a key post-enrollment consequence ('fixed at enrollment'), and the commission eligibility condition. It does not describe the response shape, but 'receive a referral code' makes the outcome clear enough.

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 100%, so the parameter names, patterns, and descriptions already carry the main burden. The description adds useful context for payout_address ('operator-controlled... fixed at enrollment') and accept_referral_terms, but agent_key is only described in 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?

The description uses a specific action and object: 'Enroll your existing agent to receive a referral code,' so an agent immediately knows the tool's job. It is distinguishable from referral_program and referral_status by the enrollment verb, though it does not explicitly name those siblings as alternatives.

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 supplies relevant context: no purchase is required, the payout address is fixed, and commission requires a message in a public non-test conversation. However, it does not state when to avoid this tool (e.g., already enrolled) or explicitly direct to speedbot_referral_status for checking enrollment state, so usage guidance is mostly implicit.

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