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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is established. The description adds genuine behavioral constraints beyond that: the API will fail or misbehave if field names are guessed, boolean fields reject 'eq' with string values, and enum filters must use documented valid values. It does not mention error behavior or result limits, but the schema independently documents limit and dryRun.

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 one-sentence purpose statement is front-loaded and the mandatory rules are numbered and scannable. Every clause earns its place — the rules target the three highest-risk failure modes. Slightly long given the schema already documents operators and collections, but the redundancy is justified because these are stated as prohibitions rather than descriptions.

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 16-parameter, nested-object tool with 100% schema coverage, the description's job is to highlight what the schema cannot: the discovery workflow, operator traps, and valid enum domains. It does that well, covering the principal blind spots for an agent. With no output schema, return-shape expectations are left unspecified, and newer features like CTEs, comparePeriods, and groupBy are not mentioned in prose — minor gaps since the schema documents them.

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 100%, so the schema carries the full burden of documenting all 16 parameters — baseline 3. The description adds real value on top by giving collection-specific valid values for common filter fields (purchases.state = SUCCEEDED|COMPLETE|PENDING|FAILED, campaigns.status = EXECUTED|DRAFT|PAUSED|STOPPED) and by constraining how the 'operator' parameter must be used for booleans, which the schema's 'value' description does not fully convey.

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+resource: 'Query event marketing analytics', then enumerates the capability surface (dimensions, metrics, time ranges, filters) and the data domains (campaigns, purchases, users). This clearly differentiates it from the many sibling lookups like nevent_get_campaign_metrics or nevent_list_campaigns, which are narrower retrieval tools rather than a general analytics query engine.

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 'MANDATORY RULES' block is exactly the guidance an agent needs: it explicitly names the sibling nevent_analytics_table_schema as an unconditional prerequisite ('ALWAYS call ... BEFORE querying'), and gives the precise boolean operator contract (is_true/is_false, never eq with strings) and concrete enum value sets for purchases.state and campaigns.status. This leaves no inference about the most failure-prone aspects of using the tool.

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