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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description reinforces this with 'This tool NEVER writes.' It goes well beyond annotations by disclosing the auto-sampling behavior, the sensitiveGate flow with acknowledge_sensitive, and the critical dry-run limitation where AI-group operations pass through unchanged — even explaining this is expected and not a bug.

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 every sentence carries essential operational detail, and the primary purpose is front-loaded in the first sentence. It is organized into distinct paragraphs for purpose, return structure, project_id handling, sensitive data gating, and dry-run limitations, making it dense but navigable with no 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?

There is no output schema, so the description fully documents return shapes: {valid, errors, warnings, dryRun}, the sensitiveGate object, and dryRun's {matchedRuleSortId, computedValue, usedAttributes}. It also covers error versus warning semantics, edge cases around sample_product absence, and points to discover_rule_operations for vocabulary — leaving no gap for an agent to call it correctly in the stated scenarios.

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 coverage is only 50%, and the rule parameter is an opaque object with additionalProperties:true while project_id has no description. The description compensates by providing the full rule document shape inline, explaining project_id's conditional requirement (inferred vs. required via list_projects), and clarifying how sample_product and acknowledge_sensitive interact with the sensitive gate — adding substantial meaning beyond the 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, action-oriented statement: 'Validate a product rule (Attribute Rule) WITHOUT saving it,' making the primary purpose immediately clear. It also distinguishes the tool from its siblings by explicitly naming create_rule and update_rule as the operations it precedes, so an agent can tell them apart without opening schemas.

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 says exactly when to use the tool: 'ALWAYS call this before create_rule / update_rule and fix every error first.' It also covers when to call alternatives (list_projects when project_id is required) and explicitly warns against using the dry-run to verify value/options mappings, routing instead to export_feed/verify_feed_attributes and repair_marketplace/run_marketplace_operation alternatives.

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