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

Annotations only declare readOnly=false, destructive=true, idempotent=true, openWorld=true; the description goes well beyond them by disclosing the preview-without-confirm behavior, the permission requirement, the cost, the owner-approval gate, and the lost-reply reconciliation protocol. The confirm gating is consistent with destructiveHint=true, not contradictory.

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?

Front-loads the core action and required values, then layers permission, cost, preview gate, and reconciliation in single-purpose sentences. Dense but every clause carries operational weight; the reconciliation clause is slightly tangential to the immediate call but justified by the idempotent write semantics.

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 confirm-gated mutation with no output schema, the description supplies what matters: permissions, cost, preview-vs-commit behavior, and stale-revision handling. It never describes the success payload or how the saved revision is returned for the next call, which the missing output schema leaves unaddressed.

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; the description adds real value by explaining the relationship between the two concurrency parameters ('if_unchanged revision from soclo_page_autopilot (or expect_absent:true when none is saved)'), i.e. the read-then-write pairing the schema documents only per-field. It does not add format or bounds detail beyond the schema, so it stops short of 5.

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 ('Save the exact displayed Website Autopilot policy base: the approved enabled and policy_mode values') and pins the scope against the sibling read tool by naming soclo_page_autopilot as the source of the revision. An agent can distinguish this write from soclo_page_autopilot_approve/reject and soclo_page_autopilot without opening any 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?

Explicitly states the precondition (needs the separate manage:autopilot permission), the cost (Free), the when-not (omit confirm to get a preview, pass confirm:true only after the owner approves), and the failure path (reconcile a lost write with soclo_page_autopilot before retrying). Both the go/no-go condition and the fallback alternative are named, leaving nothing to inference.

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