session_start

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that this is an asynchronous run returning run_id plus a wait_cmd to run in a background shell, and that edit mode creates a worktree unless isolation='none'. It omits other traits an agent needs: what happens when a run is busy but queue_if_busy is false, cost/budget enforcement behavior, concurrency limits, and side effects of edit mode on the working tree.

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 tight sentences with zero filler: the action, the return contract, and the safety-mode caveat are all front-loaded. Every clause carries information an agent needs before invoking.

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 22-parameter, no-annotation, long-running job tool, the description is too thin. Output schema coverage excuses explaining return shapes, but the description still leaves queueing behavior, cost control, concurrency, and most parameter meanings undocumented, so an agent cannot configure a run confidently from this definition alone.

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 only 27% across 22 parameters, so the description must compensate and largely does not. It only illuminates mode and isolation; the other high-impact parameters (priority, notify, notify_ref, trust, effort, max_turns, allowed_tools, timeout_min, idle_timeout_min, fallback_model, json_schema, name_slug, chat_hint, queue_if_busy) get no explanation in either the schema or the description.

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 ('Start a new headless Claude Code run') plus the immediate consequence ('Returns run_id and a wait_cmd'). The 'start' verb is unambiguously distinct from the sibling set (ack/status/list/tail/result/send/stop/wait), so an agent can route to it without opening the 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?

The description conveys mode semantics (default read-only; edit mode uses a git worktree unless isolation='none') and that runs can be queued, which implies usage. But it never says when to choose session_start over session_send for dispatching work, nor any prerequisites or exclusions. Usage is implied rather than stated.

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