Conversion Funnel

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

Annotations already indicate readonly, idempotent, non-destructive. Description adds essential behavioral details: evaluation order matters, returns empty counts on no match, and prerequisites (needs events flowing) beyond what annotations provide.

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?

Four sentences, all adding value: purpose, usage guideline, prerequisite, parameter help. Front-loaded with main function. Slightly wordy but no redundancy.

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?

No output schema, but description explains return metrics (distinct users, conversion %, drop-off) and empty behavior. Mentions prerequisite and sibling tool. Could hint at pagination or ordering details, but sufficient for agent to invoke correctly.

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 covers all 3 parameters with descriptions. Description adds valuable context: suggests calling with no steps to get menu, clarifies window_days default and valid range (1-365), and explains product_id optionality referencing whoami.

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?

Description clearly states the tool builds a conversion funnel with specific metrics (distinct users, step-to-step conversion %, drop-off) and explicitly distinguishes from sibling tool analyze_paths by stating it pairs with it to see where drop-offs go.

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?

Provides explicit when-to-use guidance: call without steps to get menu of events, pairs with analyze_paths, requires product-analytics events, and explains behavior when no events match.

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