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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds real value beyond that: it names the returned artifacts, warns the call can take 'up to a couple of minutes' (latency expectation), and notes the Premium plan requirement. It stops short of describing pagination or per-item limits.

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?

Four compact sentences, front-loaded with the action and resource, then returns, then the no-side-effects guarantee, then latency and plan constraints. No sentence is redundant or padding.

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?

With no output schema, the description carries the return-value burden and does so by naming the three kinds of results. Latency and plan gating are also covered. The only minor gap is volume/limit behavior for large accounts, which an agent might want to know.

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?

There is a single required parameter ('client') with 100% schema description coverage, which already tells the agent to pull the name from list_clients. The description only restates 'for one client' and adds no format, casing, or ambiguity guidance, so baseline 3 is appropriate.

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 (preview) and a specific resource (Autopilot's Google Ads clean-up for one client), then enumerates what the preview actually contains: keywords it would pause, search terms that spent with no conversions, and proposals needing human review. This clearly separates it from siblings like autopilot_run (applies) and audit_client (audits).

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 implied rather than stated: 'Changes nothing' signals this is the safe pre-flight step before autopilot_run/autopilot_approve, and 'Premium plan' flags a prerequisite. However, no sibling is named and there is no explicit when-to-use vs when-to-skip instruction, so the agent must infer the ordering itself.

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