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

Goes well beyond the annotations (openWorldHint, idempotentHint, destructiveHint=false) by disclosing the full-batch failure protocol: do not schedule a partial carousel, retry the unchanged batch with the same idempotencyKey and refreshed URLs, saved files are reused. It also adds the hard constraint never to invent URLs from image identifiers or sandbox paths, which is exactly the kind of non-obvious failure mode an agent needs.

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?

Front-loaded with purpose and limits, then next-step routing, then failure behavior. Every sentence carries distinct operational information with no restatement of the schema 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 write tool with an output schema already documenting return shape, the description still supplies the critical operational context: size/count limits, ordering, downstream consumers (create_draft, prepare_campaign), all-or-nothing success, and retry semantics. Nothing essential for a correct call is missing.

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%, so the description carries the burden. It explains that the files array is ordered (carousel slide order), capped at 10 items and 20 MB per file, that download_url must be a real URL, and how idempotencyKey drives retry behavior. The required brandId is never mentioned, leaving one of three parameters unaddressed.

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 (Import) plus resource (1–10 images/videos as a batch), the source (ChatGPT file handoff), the ordering semantics (carousel slide order) and the per-file size cap. An agent can immediately separate it from the singular sibling import_media and from scheduling tools like schedule_post.

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?

"Use for multiple attachments" and "generated images only when the host provides real file download URLs" give clear selection conditions, and "Does not schedule or publish" sets a boundary. It does not explicitly name import_media as the single-file alternative, so routing between the two is inferred rather than stated.

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