start_detached_capture

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

Annotations already convey read/write, idempotent, destructive, and open-world hints. The description adds the useful behavior that the call does not stay open and that reconnection is via run_id. However, it does not explain the destructive implication or what happens to existing runs.

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 short sentence that packs the key async/reconnect behavior without fluff. The phrasing is a bit cryptic, but it is efficiently sized.

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 tool with destructive/async behavior and two required parameters, this one-liner is inadequate. It lacks context about what a detached capture is, when to choose it, and how the idempotency key should be constructed.

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 0%, and the description does not explain plan_id's meaning or the idempotency_key requirements (pattern, length). It only vaguely alludes to a 'current plan' and 'once', which is insufficient to use parameters correctly.

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 the tool 'starts' a 'plan' and mentions reconnecting by run_id, giving a clear verb and resource. However, the phrase 'one current plan once' is awkward and ambiguous, and it does not explicitly mention 'capture' or distinguish this from synchronous start alternatives.

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?

No guidance on when to use this tool vs. execute_capture_plan, get_detached_capture, or other siblings. The context implies asynchronous start, but no explicit when/when-not or alternative references are given.

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