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

Beyond the annotations, it discloses the key operational behavior: the referral is queued for human review rather than processed through automatic sending. This prevents the agent from implying that a referral, notification, or prospect contact has already been transmitted.

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?

Two short sentences front-load the action and then state the most important behavioral caveat. There is no redundant or speculative wording.

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 flat-input submission tool, the description supplies the workflow and delivery expectations needed to invoke it responsibly. The fully documented input schema, annotations, and presence of an output schema cover the remaining structural details.

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 the structured fields already explain all six parameters, including optional prospect details and the notes restriction. The description adds no further parameter-level meaning, making the baseline score 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?

The description gives a specific action, resource, and outcome: queuing a partner referral for staff review. It does not explicitly distinguish this workflow from siblings such as leave_lead_note or open_support_request.

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 partner-referral and staff-review context makes the intended use case clear, while 'Nothing is sent automatically' warns against using it with an expectation of immediate outreach. It stops short of naming conditions or alternatives for choosing this tool over another request or note tool.

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