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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses rich behavioral detail: it operates on the latest pending draft if present, otherwise previews published rules in memory without creating a draft, and marks such previews as not publishable. It also explains return fields per mode, the draftPersisted flag semantics, and the relationship between position and ruleIndex. No contradiction with annotations exists.

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 is long but dense, and almost every sentence adds necessary information for an 11-parameter tool with no output schema. It is front-loaded with the core purpose and includes three concrete examples. It loses a point for being a wall of text with some minor redundancy around persistence, though the length is largely justified by the tool's complexity.

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 carries the full burden of explaining return values, and it does so thoroughly: summary, totals, howToRead, topValues, dailyTotals, and scope.explanation are all mentioned. It also covers edge cases like targeting leftover rules, draft persistence states, costMetric aliases, and time-window selection. Nothing an agent needs to invoke this tool correctly is missing.

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?

Although schema description coverage is 100%, the description adds substantial meaning beyond the schema: virtualDimensionId maps to id from list/get/search, datePreset uses the same enum as dashboards, from/to share shape with query, ruleIndex is equivalent to position, costMetric accepts aliases, and currency should match prior query calls. This far exceeds the baseline for a fully documented schema.

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: 'Preview per-rule costs or a groupBy breakdown (read-only BigQuery).' It clearly names the two modes and explicitly distinguishes this preview tool from create/update/publish siblings by stating that preview alone does not persist. This leaves no ambiguity about what the tool does.

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 provides explicit when-to-use guidance: call after a successful create/update, use update_virtual_dimension_draft or create_virtual_dimension_draft to publish, and prefer ruleId over ruleIndex. It also gives concrete exclusions, such as datePreset being mutually exclusive with from/to, and explains how to discover valid groupBy values via search. This is exemplary routing and precondition guidance.

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