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

Beyond the annotations, it discloses synchronous waiting, a 120s budget, the ownership restriction, and scheduled behavior for shared Data Sets. Especially useful is the non-throwing failure protocol—`status` is "error" and `lastError` explains why—together with the recovery path through dataset_update.

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 front-loads the operation and timing, then logically covers failure handling, use cases, and the ownership exclusion. Despite being information-dense, every sentence serves a distinct invocation or result-handling need without filler.

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 one-parameter tool without an output schema, it supplies nearly all essential operational context: source behavior, time budget, error fields, remediation, and permissions. The main residual ambiguities are what happens when the 120s budget is exhausted and what a successful outcome contains.

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 already fully describes the sole `name` parameter, including obtaining it from dataset_list. The description adds an eligibility constraint absent from the schema—the named Data Set must be owned rather than merely shared—though it provides no additional naming syntax.

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 opening sentence gives a specific action and resource: rebuild an owned Data Set by re-running its SQL or SaaS selection, and wait for the outcome. Later references to dataset_update, dataset_query, and dashboards further distinguish refreshing from editing or reading data.

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 explicitly says to use the tool after dataset_update changes the SQL or when current data is required before a dashboard or dataset_query read. It also supplies a clear exclusion: a Data Set merely shared with the caller is refreshed on its owner's schedule, not by the caller.

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