Put an image or a video on an ad

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

The description adds substantial behavioral context beyond the annotations: the three-step video flow, the fact that every step reports success independently, the undocumented requirement to resend headlines/texts when updating an ad, the tool's behavior of reading the ad first, its avoidance of a legacy collapsing field, and its post-operation readback. No contradiction with annotations exists.

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 front-loaded with the core purpose and then uses each subsequent paragraph to explain non-obvious behavior that materially affects how an agent invokes the tool. The length is justified by the complexity of the operation, and there is no filler or repetition that weakens it.

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 multi-step mutation with no output schema, the description covers the workflow, hidden API requirements, safety around the legacy field, and the final headline-count readback. The main gap is that the 'confirmation' parameter is not explained in context—an agent still does not know when a refusal occurs or when confirmation must be supplied.

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 100%, so the baseline is 3. The description adds minimal per-parameter detail: it clarifies that images and videos are local path-based files, but it does not explain when 'confirmation' would be needed or what triggers the refusal. The schema already carries most of the parameter meaning.

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 and resource: 'Attach local images or videos to an existing ad'. It also distinguishes the tool by saying it does 'the whole chain rather than one call', so an agent can tell this is a high-level composite operation rather than a single upload/update call.

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 intended use is clear from the opening sentence: use this tool when attaching local media to an existing ad. It explains that videos require a three-step chain and that this tool handles it in one call, which implicitly guides an agent away from doing separate upload/create/attach calls. It does not name explicit alternative tools or exclusions, so it stops short of a 5.

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