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

The description adds context beyond annotations: it specifies that actions involve generating codes (write), sending SMS (destructive potential?), tracking, and checking. It also notes the plan requirement. Annotations already indicate non-read-only and non-destructive, so the description complements without contradiction.

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 a single sentence that efficiently covers the tool's core functionality and a prerequisite. It is front-loaded with the main verb 'manage' and lists actions compactly. Minor improvement could be structuring as bullet points, but it is concise and clear.

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?

Given the tool has an output schema and the description covers the main actions and a requirement, it is fairly complete. It doesn't detail return values, but the output schema likely handles that. Overall, sufficient for an agent to use the tool 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?

Schema coverage is 100% and each parameter is already described. The description restates the actions but does not add new semantic details beyond the enum values. Baseline 3 is appropriate given the schema's completeness.

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 clearly states the tool's purpose: managing a referral program. It lists specific actions (generate codes, send invites, track usage, check rewards) which distinguishes it from potential siblings like ecosystem.referral_link that may only handle link generation. The verb 'manage' and resource 'referral program' provide a specific scope.

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 includes a key prerequisite ('Requires Growth+ plan') and lists the available actions, giving clear usage context. While it doesn't explicitly exclude alternatives, the actions are well-defined, helping an agent decide when to invoke this tool over other workflow or referral tools.

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