Upload an asset to a Meta ad account

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

The description discloses that the tool creates assets (uploading to asset library) and the output mapping (image hash or video id). Annotations indicate readOnlyHint=false and openWorldHint=true, which align with the description's indication of side effects. No contradictions, and the description adds context beyond 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 three sentences with no wasted words. It is front-loaded with the primary purpose, then details on bulk/single, URL types, and output. Every sentence earns its place, making it efficient and easy to parse.

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?

Given the tool has an output schema, the description does not need to detail return values but does mention image hash/video id. It covers prerequisites (upload_file for local files, adAccountId from list_meta_pages) and bulk limits. Missing details like size limits or error handling, but these are not critical for core understanding. Overall, it is fairly complete for its complexity.

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%, but the description adds significant value: it explains the relationship between url and urls (single vs bulk), accepted URL types (public https, data: URI, /generated path), that kind is inferred if omitted, and that adAccountId comes from list_meta_pages. This enriches the agent's understanding beyond the schema.

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 clearly states the tool uploads creatives (finished ads or arbitrary user files) to a connected Meta ad account's asset library, using specific verbs and resource. It distinguishes from sibling tools like upload_file by mentioning local file handling, and from other ad tools by specifying the destination.

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 explains when to use the tool (uploading assets for later campaigns) and provides an alternative for local files (use upload_file first). It also tells the source for adAccountId. However, it does not explicitly state when not to use this tool, such as for asset management or deletion, but the context is sufficiently clear.

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