evaluate_query

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

Beyond the readOnlyHint annotation, it discloses that evaluation is fresh (not cached), that only part of the query may be evaluated when `step` is provided, and that output includes columns, types, and sample rows. It also hints at error-discovery behavior when evaluating step by step.

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?

Two sentences with no filler: behavior first, then targeted use cases. Every clause adds information, and the key parameter is named inline.

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?

The tool has 8 parameters, no parameter descriptions in schema, and no output schema, so the description carries a heavy burden. It covers the core behavior but omits many parameters that an agent may need, especially `ignore_privacy_levels`, `profile`, and `count_rows`.

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?

With 0% schema description coverage, the description needed to explain parameters. It clarifies `step` and implies `rows` via 'sample rows', but leaves `source`, `profile`, `count_rows`, `timeout_seconds`, and `ignore_privacy_levels` unexplained. The prose does not compensate for the schema's lack of parameter descriptions.

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 clearly identifies the action (evaluate a query), the optional limit (`up to step`), and the result (columns, types, sample rows). It does not explicitly distinguish itself from similar siblings like evaluate_steps or preview_query, but the intended behavior is unambiguous.

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 gives concrete use cases: fetching real column names before apply_transform, inspecting step effects, and locating the first error by evaluating step by step. It does not state exclusions or alternative tools, but the guidance is specific enough to select this tool.

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