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

Annotations only declare the safety profile (write, openWorld, non-idempotent, destructive). The description goes well beyond them by disclosing the async contract: an immediate acceptance plus durable task_id rather than a completed answer, continued execution after MCP disconnects, and queueing behavior for follow-ups.

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?

Six short sentences, zero filler, with the primary capability front-loaded and the most consequential agent-facing fact (you get a task_id, not an answer) immediately after. Each sentence carries a distinct operational fact.

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?

There is no output schema, and the description covers what an agent needs about the return value and where the real result lives (get_agent_task, get_agent_conversation). For a non-idempotent, open-world write tool it also discloses persistence and impersonation limits.

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 67% (agent_id and conversation_id are documented; message is not). The description compensates meaningfully for conversation_id by defining the omit-vs-supply semantics, which the schema does not, but it says nothing about the message payload beyond it being required.

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 and resource ('Talk to an existing agent or assign it work') and immediately qualifies the scope with 'using its normal tools, memory, permissions and team'. This distinguishes it from siblings like list_agents, get_agent_task, get_agent_conversation, and schedule_agent_task without the agent needing to open 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 explicit routing rules: omit conversation_id to start a new owner conversation, supply it to continue; poll get_agent_task and read get_agent_conversation for the real answer; busy conversations queue. It also names the explicit prohibition (customer conversations readable but not impersonatable), which is valuable when/when-not guidance.

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