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

With no annotations, the description carries the full burden. It discloses that the data is cached, that results are bounded, and that evidence and source fields are per-connection. It explicitly warns about limitations: cache does not prove ownership or permissions, shared BC membership is not an asset link, and missing matches are not definitive. It also states no source refresh or write occurs. This is exemplary transparency.

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 every sentence is purposeful. It is front-loaded with the core purpose, then details selection rules, limitations, and alternatives. It avoids repetition and uses clear structuring, including an example. Despite its length, it is efficient and well-organized.

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, the description explains what is returned (bounded nodes and edges with evidence) and covers pagination, coverage inspection, and exclusions. It also states the exact selectors and their meaning. Given the complexity and lack of schema/annotations, this is as complete as an agent needs.

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?

The schema has zero description coverage for its 8 parameters, but the description explains each selector and the limit/cursor semantics. It states that exactly one selector must be provided, clarifies the behavior per selector type, and specifies limit range and pagination rules ('Follow next_cursor serially with identical selector and limit'). This fully compensates for the schema gap.

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 precise statement of the tool's function: 'Read the authenticated tenant's cached TikTok asset topology.' It then specifies the exact selectors (bc_id, advertiser_id, etc.) and explicitly contrasts with Meta's counterpart, clearly distinguishing it from sibling tools. The example reinforces the intended usage.

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 explicit when-to-use guidance: 'Provide exactly one native ID selector' and names which selectors are valid. It warns that 'Names are not selectors' and explains how BC/account/connection selectors differ from app/pixel/identity selectors. It also says to use TikTok selectors, not Meta identifiers, and routes creative upload to other tools. This is model guidance.

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