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

Goes well past the annotations: it discloses the destructive detail that the previously assigned agent is replaced, that replies are drafted rather than sent when the inbox's `replies` is `draft`, the failure mode `ai_unavailable`, and that the inbox is returned. These are concrete side effects an agent needs before invoking a destructive write.

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?

Front-loads the action and packs genuine information into each clause — replacement behavior, draft mode, user confirmation, error code, return value — with little filler. The middle sentence is dense but every clause earns its place.

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 destructive, open-world mutation with no output schema and fully documented params, the description covers side effects, the confirmation requirement, an error case, and the return value. Minor gaps remain (permission requirements, effect on in-flight conversations), but nothing essential is missing.

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 both required params are already documented (agentId from list_agents, entryPointId from list_agent_channels). The description adds no syntax, format, or source detail beyond the schema, so baseline 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?

States a specific verb (turn on AI replies) and resource (inbox), and pins down the exact mechanism: assigning the inbox to this agent and replacing whoever answered it before. An agent can distinguish this from deploy_agent or pause_agent without opening a schema.

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?

Gives a clear precondition ("Confirm with the user first") and an outcome rule for the case where the inbox can't be answered (ai_unavailable / answerable: false). It never explicitly names alternative tools such as deploy_agent or pause_agent, so routing is implied rather than spelled out.

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