Look at an ad's images

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

Annotations already mark it read-only, idempotent, and non-destructive, and the description adds meaningful runtime behavior: carousels return each card in order, video ads report that they have no still, and the tool needs no API key. These disclosures go well beyond the annotations and help an agent predict outcomes.

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, then moves to use cases, edge behavior, and authentication. Every sentence contributes either usage guidance or behavior; there is no repetition or 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 read-only image-retrieval tool with no output schema, the description covers what is returned, the carousel order, the video fallback, input provenance via schema, and authentication. An agent has enough to decide when to call it and what to expect.

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 schema already documents limit, country, and library_id clearly. The description adds carousel ordering and video behavior but no extra parameter-specific meaning beyond what the schema provides, so the baseline 3 applies.

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 and resource: 'Return the actual images from one ad so you can see them.' It also distinguishes the tool from copy-focused siblings by framing it against 'rather than only reading its copy,' and grounds it in visual questions like 'visual hook, layout, product shot.'

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 explicitly says when to use it: 'when the question is about what an ad looks like,' with concrete examples. It also states when not to expect results ('Video ads have no still to show') and that no API key is needed. However, it does not name sibling tools like get_ad or transcribe_ad as alternatives, only contrasting with 'reading its copy' indirectly.

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