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

Annotations only cover readOnly/idempotent/destructive/openWorld; the description goes well beyond them by disclosing billable AI usage, synchronous execution, task support forbidden, the three mutation modes, and a partial-failure policy (completed_items_not_rolled_back). It also explains idempotencyKey derivation behavior, which materially changes how an agent should retry.

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?

Purpose and routing are correctly front-loaded in the first two sentences, but the remainder is padded with generic orchestration boilerplate (assistantSummary-first, never display raw JSON, mention IDs only when useful) that is not specific to this tool and inflates the definition. The dense metadata block earns some of its space, but the response-formatting prose does not.

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?

An output schema exists, so return values need not be described, and the behavioral block covers cost, execution mode, and failure semantics for a high-complexity tool. However, with 27 parameters, 5 required, two enums, and nested objects at 0% schema coverage, the definition is materially incomplete on the input side, which is the main thing an agent must get right here.

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 description coverage is 0% across 27 parameters, including nested brand and doohContext objects, so the description carries the full burden of explaining parameters and largely does not. Only idempotencyKey receives any treatment; required fields like audience, KPI, funnelStage, objective, and the billing/channel enums get no semantic guidance, leaving most of the surface undocumented.

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 first sentence states a specific verb ('plan and create'), a specific resource ('an initial Studio creative set'), and a scope constraint ('for a campaign that has no saved creatives'). It explicitly names the sibling it must not be confused with (build_ad) and the disambiguating condition, so an agent can separate it from the other ~80 build/create tools without opening a 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?

States when to use (a campaign with no saved creatives), when not to use (rebuilding existing creatives), and the concrete alternative with its required arguments ('use build_ad with campaignId or campaignName'). This is exactly the when/when-not/alternative pattern, with nothing left to inference.

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