Take a conversation over from the AI

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

Beyond the annotations (mutating, idempotent, destructive), the description discloses concrete effects: stops the AI, notifies the visitor, and implies a workflow. It also mentions a prerequisite (Standard plan). This adds meaningful behavioral context not encoded in 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?

Three concise sentences that cover purpose, side effect, workflow, and requirement. No unnecessary words or repetitions. Well-structured and easy to parse.

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 tool with one parameter, the description covers the key aspects: what it does, the side effect, the follow-up actions, and the plan requirement. It doesn't elaborate on error cases or return values (no output schema), but that's acceptable given the simplicity.

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 single parameter session_id is already described in the schema as 'Session id from list_active_sessions.' The description does not add further parameter details, but the schema coverage is complete, so the baseline of 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?

Clearly states the action: 'Stop the AI answering one conversation so a human can reply instead.' It also mentions the side effect of notifying the visitor, making the purpose unambiguous and distinct from siblings like send_agent_reply or release_conversation.

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?

Provides usage context by indicating when to use it (when a human needs to take over) and gives subsequent steps: 'Use send_agent_reply afterwards, and release_conversation when done.' It also notes the plan requirement. However, it doesn't explicitly contrast with alternatives like 'use send_agent_reply without taking over.'

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