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

Annotations already declare non-idempotent, destructive and open-world, but the description adds real substance beyond them: the duplicate-on-retry consequence, the POST /api/members endpoint, the returned referral code/share URL, and the crucial fact that send_confirmation_email sends a message to a real person with a false default. That last point is exactly the kind of side effect an agent needs before invoking a destructive tool.

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?

Leads with a 'WRITE:' marker, then packs return behavior, idempotency risk, the email side effect, and the endpoint into a compact block. No sentence is filler and the highest-risk information is not buried.

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?

Despite having no output schema, the description names what comes back (member plus referral code and share URL). It covers the mutation's risk profile, the one parameter with human consequences, and the underlying endpoint, leaving nothing an agent needs before calling it.

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 baseline is 3; the description goes further by framing send_confirmation_email as an outbound message to a real person rather than just a boolean, which raises the stakes of a parameter the schema treats mechanically. It does not discuss program_id, external_id, or custom referral_code, but those are already well documented 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?

States a specific verb and resource ('creates a new member (advocate) in a referral program'), plus the return payload (member with referral code and share URL). This clearly separates it from referralrock_update_member, referralrock_list_members, and the referral-creation sibling.

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?

Makes clear this is the path for adding a brand-new member and warns that a repeat call may duplicate or fail, which steers the agent away from blind retries. It does not explicitly name update_member as the alternative for existing members, so it stops short of full when/when-not routing.

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