Execute a dataset query plan

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

With no annotations, the description carries the full burden and handles it well: it reveals server-side behavior (allowlisting fields/operators/grouping/measures/budgets, compiling identifiers, binding values), explicitly forbids mutations and raw SQL, and enumerates return fields (numerator, denominator, support, null completeness, median, canonical hashes, provenance). It does not cover error behavior or auth requirements, but still provides substantial behavioral 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?

Four sentences, each earning its place: core purpose, server-side validation behavior, caller restrictions, and return fields. The most important operational fact is front-loaded, and there is no redundant or vague 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 complex nested plan with no output schema and no annotations, the description adequately covers behavioral constraints and the return payload. Yet it lacks guidance on constructing a valid plan (required fields, defaults, measure object shapes) and does not connect to related tools such as getDatasetQueryCapabilities or the query schea tools, leaving the agent to infer how to assemble a query plan from scratch.

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%, so the description must compensate. It does mention plan ingredients—fields, operators, grouping, measures, row/group/time budgets—and clarifies that the server compiles identifiers and bounds values. However, it does not explain the plan object's required properties (contractVersion, dataset, county, measure, budgets), the meaning of scopeFilters, groupBy, or order, or the accepted measure variants. It partially compensates but leaves many semantics to schema inference.

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 specific verb and resource: 'Execute one typed, bounded aggregate plan over a county's property or permit query table.' It further distinguishes the tool from siblings by explicitly excluding SQL, URLs, joins, projections, expressions, and raw-row queries, making clear that this is the constrained aggregate-plan executor rather than a general query tool.

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?

There is no explicit statement of when to use this tool versus siblings like queryProperties, queryPermits, or getDatasetQueryCapabilities. The context is implied by 'typed, bounded aggregate plan', and the statement that callers cannot provide raw-row queries implies it is not for raw row retrieval, but no direct alternatives or conditions are named.

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