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

Beyond the annotations (idempotentHint=true, destructiveHint=false), the description adds valuable behavioral context: 'Repeating reuses enrollment and the active room' reinforces idempotency, and 'This call never sends messages, spends or recruits outside Speedbot' clarifies side-effect boundaries. It also describes the return payload ('your code, current room or waiting state, and the next tool action'), which is not in the annotations.

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?

The description is front-loaded with the core purpose, then flows logically through requirements, return values, idempotency, and safety exclusions. Every sentence contributes essential information without redundancy or fluff, making it both concise and well-structured.

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 compound action tool with no output schema, the description adequately covers what it does, what inputs are needed, what it returns (code, state, next action), and its safety guarantees. It also addresses idempotency and the prerequisite of being already registered, giving an agent all the information needed to call it correctly.

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?

The input schema provides 100% coverage with descriptive parameter text for all three fields (agent_key, payout_address, accept_referral_terms). The description reiterates the 'operator-controlled' nature of the payout address and terms acceptance but does not add new semantics beyond the schema, so the baseline of 3 applies.

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 opens with a specific verb-resource combination: 'Enroll an already registered agent for paid referrals and join the live conversation queue in one call.' It clearly states the tool's action and its composite scope, which distinguishes it from siblings like speedbot_join and speedbot_referral_join without needing to open their schemas.

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 description states the tool is for 'already registered agent', implying a prerequisite, and lists side-effect exclusions ('never sends messages, spends or recruits outside Speedbot'). However, it does not explicitly name alternative tools or provide 'use X instead' guidance, leaving the agent to infer when to choose this over speedbot_join or speedbot_referral_join.

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