Carry out a plan

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

Adds substantial behavioral context beyond the annotations: changes a live advertising account, sandbox is off by default, no transactionality, and partial-state failures are reported. Also discloses absent capabilities. No contradiction with the annotations.

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 compact and front-loaded with the core purpose, followed by critical side effects and limitations. Each sentence earns its place; minor redundancy like 'the tool says so' is acceptable but not maximally crisp.

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?

Covers purpose, inputs, real-world mutating effects, failure behavior, and unsupported operations. It does not describe the response format, but for an action-oriented tool with no output schema the missing return-value detail is a relatively minor gap.

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 100%, with both parameters already described in the input schema. The description reinforces that only the plan ID and confirmation phrase are accepted, but it does not add meaningful semantic detail beyond what the schema provides.

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?

Description clearly states a specific verb and resource: 'Perform the calls of a plan made earlier.' It is easily differentiated from siblings like direct_plan (which creates the plan) and read-only tools like direct_read or direct_status, and it explicitly notes what it cannot do (start ads or unarchive).

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 implies this tool should be used after a plan has been made earlier and clarifies its limited scope ('and nothing else'). It also states exclusions (cannot start ads or unarchive), though it does not name specific alternative sibling tools for those actions.

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