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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value beyond that: it lists the three categories of content returned and discloses that the engine runs nightly and is gated to pro/premium plans, which affects whether the call will be meaningful for a given account. Minor gap: no note on empty-state behavior for accounts without autopilot enabled.

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?

Two compact sentences, front-loaded with what is returned, followed by the minimum context needed to interpret 'autopilot'. No redundant restatement of the name and 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 zero-parameter read with no output schema, the description gives a usable picture of return contents and the plan prerequisite, which is what an agent needs to call it and interpret results. It would be fully complete if it told the agent how this differs from the review/runs listing siblings.

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?

The tool takes zero parameters, so there is no parameter meaning for the description to add; baseline 4 applies. Nothing in the description misdescribes the input shape.

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?

Names a specific verb ('get') and resource ('autopilot') and enumerates the returned payload: config, queued ideas, and drafts pending review. It also defines what autopilot is, so an agent unfamiliar with the product understands the object. It stops short of distinguishing itself from close siblings like list_autopilot_review, which by name appears to cover the 'drafts pending review' portion.

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?

Usage is only implied: check overall autopilot state. There is no statement of when to call this versus list_autopilot_review, list_autopilot_runs, or configure_autopilot, which is a real overlap given the 'drafts pending review' content. The parenthetical '(pro/premium plans)' is a useful eligibility prerequisite but is not usage guidance toward alternatives.

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