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

With no annotations provided, the description carries the full burden. It discloses key behaviors: async video processing, auto-grouping via pair, and auto-detection of type. However, it omits other behavioral traits like what the response contains, whether uploads are idempotent (despite an idempotency_key parameter), or any permission requirements. It's adequate but not exhaustive.

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 zero fluff. It front-loads the purpose, then immediately gives the most critical constraint (exactly one source), then the pairing and async notes. Every sentence earns its place; no redundancy with the schema.

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's complexity (8 params, async behavior, pairing), the description covers the essentials: source selection, pairing, and async status check. It does not mention the return value (no output schema, so not required) or idempotency semantics, but for an upload tool this is a solid level of completeness. It could be more thorough about what happens after upload (e.g., returns an ID) but that is not critical.

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 75% (6/8 params described), so baseline is 3. The description adds meaningful extra semantics beyond the schema: it explains the exactly-one constraint, elaborates on the pair grouping behavior, and notes that type is auto-detected if omitted. This compensates for the two undocumented parameters (ad_account_id, idempotency_key) partially, but those are fairly self-explanatory.

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 action ('Upload image/video from Google Drive or Dropbox to a Meta ad account') with a specific verb and resource. It distinguishes this from siblings like adsap_google_upload_asset or adsap_import_account_creatives by specifying the source (Drive/Dropbox) and destination (Meta ad account), making its unique purpose unambiguous.

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 provides explicit usage constraints: 'Provide exactly one of drive_file_id / dropbox_path' and instructs on the async nature ('Videos are async — check with adsap_get_upload_status when complete'). It also explains the pairing behavior. It does not explicitly list when not to use this tool versus alternatives, but the constraints are clear enough for an agent to decide.

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