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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description discloses two substantive behaviors an agent cannot infer: the server-side budgetCeiling validation against the account's monthly spend ceiling with the specific AD_BUDGET_CEILING_EXCEEDED error, and the caveat that AI-generated creatives still require approval before publish even on autopilot. These are exactly the kind of failure-mode and expectation-setting details that matter.

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?

Three sentences with zero filler: purpose is front-loaded in sentence one, the config requirement and validation behavior follow, and the creative-approval caveat closes. The structure mirrors how an agent should reason about the call — what it does, what it requires, and what to watch out for.

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 tool with a conditional nested object and no output schema, the description covers mode semantics, config requirements, a failure mode, and a behavioral caveat — enough to invoke it correctly. It stops short only of describing the return value and how an autopilotConfig is handled when mode is 'copilot', which are minor gaps given the schema and annotations carry the rest.

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 80% (only adCampaignId is undocumented, and its name is self-explanatory). The description adds genuine value beyond the schema by explaining that budgetCeiling is validated server-side against the account's monthly spend ceiling and reinforcing the dependency between automationMode='autopilot' and the autopilotConfig fields.

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 opens with a specific verb+resource ('Set an ad campaign's automation mode') and precisely defines the two modes — 'copilot' (AI suggests, human acts) vs 'autopilot' (AI acts within explicitly granted capabilities) — differentiating it from the more generic campaignstack_update_ad_campaign sibling. An agent can tell exactly what this tool is for without opening the 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?

The description conveys clear operational context: it states when the tool applies (switching automation mode) and gives the conditional rule that autopilot requires autopilotConfig with a goal and capability booleans. It doesn't explicitly name alternative tools or state when not to use it, but the mode semantics and config requirements make the intended usage unambiguous.

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