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

Adds substantial behavior beyond the annotations: it locks the conversation to the chosen client, re-checks the limits set via autopilot_set on every call, records out-of-limit actions as proposals instead of executing them, and does nothing in shadow mode. The 'no separate AI cost' and premium-plan note are also useful operational facts that the readOnlyHint=false / openWorldHint=true flags cannot convey.

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?

Purpose and workflow are front-loaded and every clause carries information. The single dense paragraph packs in guardrail, shadow-mode, and cost details, which slightly reduces scannability, but there is no filler.

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 stateful, mutating entry point with no output schema, the description covers the return payload (briefing sections plus instructions), the side effect (conversation lock), the guardrail behavior, the shadow-mode no-op, and the required follow-up tool. An agent has everything needed to call and sequence it correctly.

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 the schema already documents all three parameters (client, focus, started_by). The description reinforces the single-client scope and ties the client parameter to the allowance set by autopilot_set, but adds no format or syntax detail beyond the schema. Baseline 3 applies.

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 with scope ('Run Autopilot on one client in THIS conversation'), and immediately marks it as the start of a flow that ends with autopilot_finish. An agent can distinguish it from autopilot_run, autopilot_preview, and autopilot_finish from the description alone.

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?

Gives explicit trigger phrasing ('Use for "run Autopilot on X" and in scheduled routines') and mandates the follow-up call to autopilot_finish, which is strong sequencing guidance. It does not, however, contrast itself against the closest siblings (autopilot_run / autopilot_preview), so the when-not is left implicit.

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