Create video ad (pipeline)

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

Annotations only flag a mutating operation (readOnlyHint=false), so the description adds real value by exposing the composite sequence and warning that promotion must stop if the intended creative failed to upload or process. It does not discuss cleanup, auth, or rate limits, but the annotations already establish the side-effect profile.

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 front-loads the pipeline in one compact arrow chain, then states the input alternatives and required field in two short sentences, followed by two terse safety commands. Every sentence earns its place with no filler.

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 7-parameter composite tool with no output schema, this is close to complete: the agent can infer account_id/line_item_id from sibling list tools, knows the creative source, and is protected from promoting wrong assets. The remaining gaps are the exact meaning of line_item_id as the existing ad group and what a successful invocation returns.

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 only 14% (only account_id is documented), so the description must compensate. It clarifies the main content inputs (media_url or inline base64 video, required text) and hints that destination_url changes the card/media step, but it leaves line_item_id and name semantically implicit and never defines media_keys.

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?

States a specific verb ('Create') and resource ('video ad') and immediately defines the composite pipeline: chunked upload → website card → nullcast post → promote onto an existing ad group. This clearly distinguishes it from image-ad creation and single-step upload/tweet/card tools.

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?

Tells the agent when this path is appropriate: new video creative on an EXISTING ad group, with either media_url or inline base64 video and required text. It gives explicit negative guardrails (STOP on failed creative; do not promote a still/source/library asset), though it does not name alternative sibling tools like x_ads_create_image_ad.

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