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

Annotations already declare readOnly, idempotent, and non-destructive, but the description adds substantive context: the autonomy envelope (pause a weak ad, budgets up to 20%, inside caps, once every 3 days per campaign) and plan gating via Scale. That is material for an agent deciding whether to act itself or defer to autopilot. It could go further on freshness or caching, but the added value is real.

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?

One dense sentence carries purpose, autonomy rules, plan gating, and the read-only constraint with no filler. The parenthetical rule list is a little crowded, but the read-only restriction is placed last where it lands with emphasis.

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 parameters and an output schema already present, return-shape explanation is unnecessary, and the description covers state, autonomy scope, plan eligibility, and who may change it. The only gap is inter-tool routing against nearby ad tools.

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 nothing to disambiguate and the baseline of 4 applies. The description correctly implies a single implicit subject (the current account's autopilot) without inventing arguments.

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 names the specific subject (autopilot state) and enumerates what it reports: whether autopilot is on, what actions it may take autonomously, and whether the plan permits it (Scale). That distinguishes it from siblings like get_ad_caps or set_ad_budget, though it never states a verb such as 'read' or 'get' up front, leaving the framing as a question rather than a statement of action.

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 clearly sets a boundary: 'Read only: the human turns it on or off on the Ads page under Caps, never an agent,' which tells the agent not to attempt changes and where the human control lives. It does not, however, say when to consult this versus ads_overview or get_ad_caps, so the positive selection guidance is only implied.

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