adopt_conversation

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

With no annotations, the description carries the full burden and does disclose two real behaviors: a lead-only authorization requirement and which app families are supported. It does not say what happens to the original conversation, whether it must be idle, what happens on name collisions, or what the call returns.

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?

A single tight sentence with the access constraint front-loaded ('Lead only.'), which is the right ordering for a gated tool. Nothing is wasted, though the payoff clause is a bit crowded into the same sentence.

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 4-parameter mutation-style tool with zero annotation coverage and no output schema, the description leaves significant holes: no return value description (agent handle/id), no role semantics, and no failure or prerequisite conditions. The agent can guess the gist but cannot call it confidently.

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 0% across four parameters, so the description must compensate and only partly does. It effectively enumerates the `app` values (codex, claude-code, antigravity) and implies `conversation_id` refers to the existing conversation, but `name` and `role` (default 'manager') get no explanation at all — the reader cannot tell what role values are legal or what a role does.

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 uses a specific verb+resource: 'Turn an existing codex, claude-code or antigravity conversation into a fleet agent', and states the payoff ('keep directing it with send_message'). It implicitly contrasts with spawn_agent by requiring an *existing* conversation, but never names that sibling, so differentiation is left to inference.

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?

'Lead only.' gives an explicit precondition for use, and the mention of send_message clarifies the intended follow-up workflow. It stops short of explicit exclusions (e.g., 'use spawn_agent to start a new agent instead'), so an agent must infer the boundary.

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