direct_write

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

With no annotations, the description carries the burden and delivers useful behavioral facts: the call is idempotent, performs a post-write readback of affected objects, and is restricted to an allowlisted service/method set. It does not mention auth/permissions or explicit side-effect severity, but the delete/archive methods make mutability clear.

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?

The description is two sentences and front-loads the core action; every clause adds a distinct fact (scope, allowlist, idempotency, readback, approval path). No filler or repetition.

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 complex mutation tool with no annotations, the description covers scope, allowed methods, idempotency, and the human-gate alternative, and an output schema exists for return values. However, an agent still lacks concrete service/method pairing rules and an item structure, which matters for a write API with only 0% schema descriptions.

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 0%, yet the description compensates partly by enumerating allowed method values, naming the object types for items, and signaling idempotency. It still leaves the exact shape of items and the allowed service values to inference, so the compensation is incomplete.

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 uses a specific verb ('apply') and a concrete resource span ('campaigns/adgroups/ads/keywords/bids'), going well beyond the terse tool name. It also distinguishes itself from direct_apply_changes by naming it as the approval-gated alternative.

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 gives actionable context: this is the autonomous path, while direct_apply_changes is the approval-gated path for campaigns:update, which tells an agent when to prefer each. It stops short of a full when-not-to-use statement or broader alternative selection guidance.

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