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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so well. It states the operation is unsaved, describes the network fan-out, the signed source_receipt with expiry, the Meta-to-TikTok naming mapping, and nuanced image-music retention/omission behavior. An agent gets realistic expectations about side effects and limitations.

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 long but densely informative; every block earns its place: core behavior, workflow, naming mapping, music edge cases, required parameters, and example. It is front-loaded with the most important function and does not repeat schema content.

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 tool with no output schema and no annotations, the description covers the full operational lifecycle: inputs, outputs, next step, expiry, and edge cases. An agent can invoke it correctly and know exactly how to hand off to templates_create without ambiguity.

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 0%, so the prose must compensate. It does by naming the required advertiser_id, clarifying that adgroup_id and adset_id are interchangeable spellings for the same TikTok value, and providing a complete example. However, the prose says adgroup_id OR adset_id is required while the schema only marks advertiser_id as required, creating a minor prose/schema mismatch.

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 opens with a specific verb and object: 'Reverse-engineer a template preview from one live TikTok adgroup.' It also names the internal fan-out endpoints, the return artifacts, and the downstream handoff, making it clearly distinct from template CRUD siblings like templates_create, templates_list, and templates_get.

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 a concrete usage workflow: review the preview, then pass extracted fields and source_receipt unchanged to templates_create before expiry. That is clear context, but it does not explicitly enumerate alternatives or exclusions, such as when to prefer fetching an existing template over reverse-engineering one.

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