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

Annotations already indicate a safe read-only, idempotent operation. The description adds valuable behavior beyond annotations: default first five rows in table order, offset/limit pagination, the rowOffset/rowCount comparison, and the caution about header-looking rows. This materially helps the agent handle returned data correctly.

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 sentences, each carrying distinct information: what is returned, how pagination works, and a critical data caveat. The description is front-loaded with the primary purpose and stays compact without fluff.

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?

With no output schema, the description takes responsibility for explaining return values and does so well: shape fields, row window, rowOffset/rowCount, and header-row caution. It provides enough detail for an agent to invoke the tool and interpret results correctly, including pagination and edge-case handling.

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 descriptions cover limit and offset, and the description reinforces their default behavior. Required projectId and datasetId have no schema descriptions, but their meaning is clear from names and the tool's purpose. The description does not add substantial new semantics for the parameters beyond what the schema already provides, and 50% coverage is only partially compensated.

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?

Description names the exact operation: retrieving a single dataset's shape and a leading window of rows. It clearly differentiates from sibling list_datasets by emphasizing 'single dataset' and enumerates the returned fields (name, row/column counts, dashboard link, rows).

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 gives clear context for when to use this tool: when you need one dataset's shape and initial rows, with pagination guidance. It does not explicitly name alternatives or say when not to use it, but the context is unambiguous enough for an agent to choose it over list_datasets.

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