agent_start

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

Annotations already disclose that this is non-readonly, non-idempotent, and non-destructive, while the description adds the idle-pane precondition and notes that extra args are passed through to the agent CLI. It still does not explain failure behavior if the pane is not idle, timeout behavior, or other side effects beyond starting the process.

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 wasted wording. The core action and key precondition are stated immediately.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. The description supplies the critical idle-pane precondition and kind examples; remaining gaps around timeout and name constraints are minor because timeout has a schema default.

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 0% across 5 parameters, so the description must carry the burden. It usefully explains kind examples and args routing, and implies pane_id must reference an idle shell pane, but it does not clarify name constraints, pane_id format, or timeout_ms semantics.

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 and resource: start a coding agent, with kind examples, in an existing idle shell pane, and name it. This clearly distinguishes it from siblings such as agent_prompt, agent_list, and pane_run.

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 an important prerequisite, that the shell pane must be existing and idle, which helps an agent avoid misuse. However, it does not explicitly say when to use this instead of pane_run, agent_prompt, or other sibling tools, nor does it describe when not to use it.

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