Run a bounded DataLens dataset query using exact field GUIDs to retrieve sample data for inspection, not chart branch validation.
Run a bounded Dataset query by exact field GUIDs; this is data evidence, not chart branch proof.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | ||
| limit | No | ||
| fields | No | ||
| offset | No | ||
| params | No | ||
| columns | Yes | ||
| filters | No | ||
| max_pages | No | ||
| dataset_id | Yes | ||
| tie_breaker_guids | No |
Changes observed during successful MCP inspections.
v1.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered structurally. The description adds a genuine behavioral caveat about the epistemic weight of results ('data evidence, not chart branch proof'), which is useful context. However, it says nothing about pagination interaction (max_pages/offset), result size limits, or cost despite 'bounded' implying a constraint.
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?
A single front-loaded sentence with the action verb first and the qualifying caveat second; nothing is wasted. The second clause is somewhat cryptic jargon, which slightly reduces how much structure is achieved per word.
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 10-parameter query tool with no output schema, no annotation gaps and zero schema description coverage, the description is far too thin — it omits how results are shaped, how paging works, and how the two required parameters relate to the rest. Adequate only in the narrow sense that annotations cover the safety profile.
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% across 10 parameters, so the description carries the full burden and only partially discharges it by clarifying that GUIDs are exact field GUIDs. It never explains the distinction between required 'columns' and optional 'fields', nor the roles of filters, params, sort, limit, offset, or max_pages.
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?
States a specific verb ('Run a bounded Dataset query') and the keying mechanism ('by exact field GUIDs'), so the agent knows it is a data-query tool rather than a metadata tool. It does not name or differentiate itself from siblings like dl_dataset_validate or dl_dashboard_snapshot, leaving that inference to the agent.
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 clause 'this is data evidence, not chart branch proof' gestures at a use boundary but never names an alternative tool or a concrete condition for choosing this over dl_dashboard_snapshot or dl_dataset_validate. An agent can only guess when this is the right call.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.