fleet_dispatch

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

With no annotations provided, the description carries the behavioral burden and largely delivers: it discloses the headless resume mechanism, dedup-per-session behavior, shared wake concurrency/circuit-breaker constraints, ledgering in wake_sessions, and the conservative idle guard with its refusal outcome (availability='live'). Minor gap: the return/response shape (beyond the availability field) isn't described, though an output schema exists.

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 thorough but somewhat dense; the safety-gate section is detailed and valuable but runs long with layered sub-clauses. It's front-loaded with the core purpose first, which is good. It earns its length overall but could be tightened without losing the essential safety/disclosure information.

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 side-effecting dispatch tool with an output schema, no annotations, and 5 parameters, the description is remarkably complete: it covers behavior, safety constraints, failure modes, concurrency limits, source of the key parameter, and explicit non-goals. This is well-rounded for the agent to make a correct invoke/no-invoke decision.

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%, giving a baseline of 3. The description adds value by explaining what an 'instruction' means in operational terms (advance task X / report status) and adds context about target_session_id's source, and clarifies max_turns/tools_level defaults behavior (tools_level 'never exceeds the requested preset'). This goes slightly beyond schema, warranting a 4.

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+resource+mechanism: 'Dispatch an operational instruction to another ship (CC session) in the fleet' via headless `claude -p --resume` on an idle session. It clarifies what the tool does (relay operational work, nudge idle ship) and what it does NOT do (no strategic decisions), clearly distinguishing it from sibling tools like task_run, channel_send, and agent_update_status.

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?

Provides explicit when-to-use guidance ('Use it to nudge an idle ship to advance a task or report its status'), explicit when-not ('NOT to make strategic decisions'), and even defines the safety gate conditions that must hold (resumable, not user-live). It tells the agent where to source the key parameter ('Get target_session_id from the fleet view / project summary').

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