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

With no annotations and no output schema, the description carries the full burden, and it does add useful non-obvious context: the multi-action dispatch model, the connect-first prerequisite, and the delegated-parameter pattern via adgpt_capabilities. It does not disclose the write/irreversibility profile of createAds or an OAuth flow for connectAccount, nor any auth or rate-limit behavior, so the safety picture is only partially covered.

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?

Two sentences, front-loaded with the connect/publish framing, but the first sentence is a dense run-on mixing two platforms plus reads and taxonomy. The second sentence re-enumerates all eight action values, which duplicates the schema enum and is redundant text. Functional, not wasteful enough to be bad, but not tight.

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 an eight-action dispatcher with no annotations and no output schema, the description is reasonably complete: it states the scope, the connect-first prerequisite, and explicitly routes parameter discovery to adgpt_capabilities, which matches the schema's own pointer. The main remaining gap is that per-action behavior and output shape are entirely offloaded, requiring a second call before the agent can act confidently.

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?

Two parameters at 50% coverage; the critical 'params' object is essentially undocumented beyond 'see adgpt_capabilities', so the description does not compensate for the gap. The action list in the description merely restates the schema enum rather than adding meaning. Guidance points the agent elsewhere, which is a valid design but adds little over the structured fields.

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 names concrete resources and verbs across the two platforms it fronts (Facebook ad-account connect/check/exchange-token, TikTok regions/languages/campaigns/ad-groups/create-ads), so an agent knows what class of operations live here. It is a dispatcher, so the purpose is a bundle rather than a single verb+resource, and overlap with siblings like adgpt_campaigns is not resolved. Still clear enough to route above the level of a vague wrapper.

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 gives one real prerequisite ('publish to TikTok from an account you already connected in the web app') and a second-hop instruction to call adgpt_capabilities with the operationId for parameters. However, it never says when to reach for this tool versus adgpt_campaigns or other siblings, which matters because several actions (campaign/ad-group reads) plausibly overlap. Usage is implied rather than bounded.

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