tiktok_get_insights

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

With no annotations, the description carries the transparency burden and does disclose a key runtime behavior: the query planner automatically splits incompatible dimension combinations with the one-ID-plus-one-time-dimension rule. It also notes 400+ metric support, but does not mention authentication, rate limits, or response format, so it is not fully 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?

Three short sentences with no filler. The main action is front-loaded, followed by resource pointers and the most important planner behavior. Every sentence adds value.

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?

The description covers metric discovery and the planner rule, which are important for correct invocation, and the schema covers most parameters. However, with no output schema and no mention of pagination, result shape, date-range limits, or when to prefer this over the raw report endpoint, an agent still has to infer some operational details.

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%, so most parameters like metrics, dimensions, dates, advertiserId, and queryLifetime already carry clear meaning in the schema. The description adds one useful cross-parameter constraint about dimension compatibility and auto-splitting, but does not explain dataLevel or limit beyond what the schema provides.

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 states the core action ('Query TikTok Ads performance insights') with a specific resource and adds 'Supports 400+ metrics' and query planning, giving it a clear identity. It does not explicitly differentiate from reporting siblings like tiktok_get_report_raw, but the metrics/dimensions resource links make the 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?

The description provides practical context by directing the agent to tiktok://metrics and tiktok://dimensions for discovering valid values, which implies how to prepare calls. It does not state when to choose this tool over sibling reporting tools such as tiktok_get_report_raw or tiktok_get_entities_raw, so alternatives and exclusions are missing.

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