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

Annotations declare readOnlyHint=true, destructiveHint=false; the description adds critical behavioral nuance: it operates on the latest pending draft if one exists (draftPersisted: true) or in-memory published rules without creating a draft (draftPersisted: false, not publishable). It also warns to read the summary field first and clarifies side effects (or lack thereof). This significantly exceeds what annotations alone convey.

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?

Despite being lengthy, every sentence carries operational value. It opens with the core purpose, flows through draft-state behavior, parameter relationships, mode-specific outputs, and ends with concrete examples. The structure is logical and dense with no filler—an appropriate size for an 11-parameter tool.

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 11 parameters, no output schema, and complex mode-dependent behavior, the description covers everything an agent needs: draft semantics, output shapes (totals.namedRulesSharePercent, topValues, dailyTotals), parameter constraints, and sibling tool relationships. It also gives examples covering typical use cases. This is complete for even a high-complexity tool.

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 coverage is 100%, the description adds deep relational semantics: virtualDimensionId source, position/ruleIndex equivalence, ruleId vs. ruleIndex preference, leftover targeting, mutual exclusivity of datePreset/from/to, currency alignment, costMetric valid values, and how to discover groupBy via search. This goes far beyond the schema's per-property 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 first sentence states a specific verb+resource: 'Preview per-rule costs or a groupBy breakdown (read-only BigQuery).' It clearly distinguishes between modes and explicitly contrasts with create/update/publish siblings via the draft vs. published state discussion. This is a textbook clear purpose statement.

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 explicitly states when to call it ('Call after a successful create/update') and when to use alternatives ('To publish changes ... call update_virtual_dimension_draft ... or create_virtual_dimension_draft ... preview alone does not persist'). It also explains the mode choice (costs vs. breakdown) and parameter selection, with examples. This is exemplary usage guidance.

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