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

Annotations already convey mutation (readOnlyHint=false), idempotency, open-world side effects, and destructiveness. The description adds 'durable' to suggest persistent execution, but it does not explain what state changes are made, what destructive effects may occur, or how the agent should observe progress. Given annotations carry the safety profile, this is acceptable but not rich.

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?

The description is a single, front-loaded sentence with no filler. It states the core action and scope immediately while leaving detailed parameter semantics to the schema, which is appropriately concise for a tool with good annotation coverage.

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?

Given the sibling tools include modem_agent_get_run and modem_agent_cancel_run, the description could usefully mention that this starts a run and that results can be checked with get_run. There is no output schema, so the agent is left to infer the return behavior. The term 'durable' hints at asynchronous execution, but the definition does not fully explain follow-up mechanics or retry behavior.

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 input schema provides complete, meaningful descriptions for all three parameters (prompt, conversation_id, idempotency_key), so schema coverage is 100%. The description adds no additional parameter-level meaning beyond what the schema already documents, so the baseline score of 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?

The description uses a specific verb ('start') and a distinct resource/operation ('a durable follow-up turn in an existing MCP conversation'), which clearly communicates the tool's function. It implicitly separates itself from siblings like modem_agent_get_run, modem_agent_cancel_run, and search_modem, though it does not explicitly name the alternative for starting a new 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?

The phrase 'in an existing MCP conversation' provides clear contextual guidance that this tool is for follow-up turns, not initial invocations or status checks. However, it does not explicitly name alternatives or state when-not-to-use conditions, so it stops short of full routing guidance.

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