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

Annotations only mark it destructive and idempotent; the description adds real behavioral context beyond them — the leave-side change is immediate and unconfirmed, the join-side requires a two-step preview/confirm, and 'Autopilot still learns from the agency's own clients' clarifies the effect isn't a full opt-out. This goes meaningfully past the annotation hints.

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 purpose is front-loaded and the four sentences are dense but each carries information (purpose, leave behavior, join workflow, invocation condition). Slightly run-on phrasing, but no filler sentences.

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 two-parameter privacy toggle with full annotation and schema coverage and no output schema, the definition covers what changes, how the confirm sequence works, and when to invoke it. Adequate and close to complete; only the lack of any reversibility/persistence note keeps it from a 5.

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 coverage is 100%, so the baseline is 3, but the description adds semantic value by tying the share toggle to the leave/join asymmetry and explaining that confirm is only required when rejoining. This meaningfully exceeds the raw boolean documentation already in the schema.

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: it controls whether the agency's clients count toward Autopilot's cross-agency shared learning, explicitly framed as the dashboard Privacy setting. That is a clear, distinctive purpose. It stops short of naming how it differs from neighbors like autopilot_preference, so it isn't a 5.

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 a clear when-to-use rule ('Only when the person asks') and lays out the conditional workflow: leaving needs no confirm and applies instantly, while joining requires a preview then confirm. No alternative tool is named, which keeps it out of 5 territory, but the usage conditions are explicit.

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