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

Annotations already declare destructive, open-world and idempotent; the description goes beyond them with the actual state machine (pending to confirmed at two events, pending to unconfirmed at three), the creation side effect when a referrer is present, and the reward-unlock consequence. It omits how repeated calls interact with event counting for a three-event goal, which is the main behavioral unknown for a mutation 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?

Front-loaded with the WRITE marker and the core effect, then state transitions, edge case, and side effect, ending with the endpoint. Six compact clauses with no filler; slightly dense but every clause carries information.

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 12-parameter mutation with no output schema, the description supplies the essential consequences an agent needs: what state the referral moves to, that missing referrals can be created, and that rewards and automations may fire. What is missing is return/response behavior and duplicate-event semantics, which matter for multi-event goals.

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%, so all 12 parameters including the required uuid and confirm are already documented. The description adds only the implicit point that referrer enables creation of a missing referral; otherwise it defers to the schema. Baseline 3 is appropriate.

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?

Opens with an explicit verb and resource ('WRITE: report a conversion event for a referral') and narrows scope to campaigns whose goal tracks two or three events, which separates it from generic siblings like confirm_referral. An agent can tell what this does and which campaign type it applies to without reading the schema.

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?

The parenthetical scoping condition ('campaigns whose goal tracks two or three events') gives clear context for when this tool is applicable, and the missing-referral behavior tells the agent it can be used on unknown referrals when a referrer is supplied. It never names the alternative tools (confirm_referral, qualify_referral) or states when NOT to use it, so no explicit routing.

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