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

Annotations already mark idempotentHint and destructiveHint, and the description adds the useful async behavior ('Returns immediately... poll ... for the result') plus a prerequisite skill read. It does not contradict any annotation.

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 sentences, each earning its place: what it does, how to get the result, and the required prerequisite. The most important behavior is front-loaded.

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 2-parameter async invocation with no output schema, the description covers the start behavior, polling path, and prerequisite skill. It could optionally mention how to continue or cancel the conversation, but nothing essential to making the first correct call 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 prompt and idempotency_key are already documented in the schema. The description adds no additional parameter semantics beyond the stable-retry-key concept implied by idempotency_key.

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 states a specific verb and resource ('Start a durable Modem agent conversation'), notes it returns immediately with conversation_id and run_id, and distinguishes itself from the polling sibling modem_agent_get_run. This makes its role clear relative to the sibling list.

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?

It gives explicit context: use this to start a conversation, poll modem_agent_get_run for the result, and read modem_skills before the first call. It does not formally enumerate when not to use it or contrast with modem_agent_send_message/cancel_run, but the start-vs-poll workflow is clear.

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