analyze_funnel

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

With no annotations, the description takes on the transparency burden. It discloses the two-stage lookup behavior, the dependency on user-defined step IDs, and the data sparsity issue (steps only appear on days players reached them), which are important behavioral traits.

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 well-structured with clear paragraphs, but contains some redundancy (e.g., repeating 'discover'). It is appropriately sized for the tool's complexity without being excessively lengthy.

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?

The description covers the full workflow, data nuances, and usage tips, giving a complete picture for a complex multi-step tool. It does not specify exact output format, but that is not required given no output schema.

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?

The input schema already provides detailed descriptions for all parameters, so the baseline is high. The description enriches understanding of time parameters by explaining why a generous range is needed, which adds meaningful context 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 clearly states the tool's function: it resolves funnels end-to-end, discovering funnels and steps, then pulling metrics and highlighting the biggest drop-off. This distinguishes it from lower-level sibling tools like query_metric by offering a composite analysis.

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 practical usage guidance, such as the need for a generous time range and the ability to omit funnelName for all funnels. However, it does not explicitly contrast with alternative tools when a simpler metric query would suffice.

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