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

Goes well beyond the readOnly/idempotent annotations by disclosing a license gate (PREMIUM), an error contract (never raises a protocol error; returns {"error": ...} with a fix hint), and retry safety after correcting input. These are traits the annotations cannot express and they materially change how an agent handles failure.

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?

Purpose, examples, usage rule, and error behavior are front-loaded and each section is short. The input/output example pair is somewhat verbose given an output schema already exists, but it is not wasted for a nested-object parameter.

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 single-parameter analytic tool this covers everything an agent needs: what it computes, when to pick it, what the response contains, and how errors arrive. Return values are additionally backed by an 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?

Schema coverage is 100% and already documents ordering, minimum stage count, and value type, so the baseline is 3. The worked input example and the sample error ('need at least 2 stages') reinforce the shape and the descending-order constraint, adding modest value over the schema text.

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?

States a specific verb+resource ('Analyze a conversion funnel') plus a second concrete outcome ('find the biggest drop-off'). It also explicitly distinguishes itself from cohort_retention and ab_test, so an agent can route without opening any schema.

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?

Gives an explicit inclusion rule ('Use when stage counts descend through one funnel') and two named exclusions with the sibling that handles each case. Nothing about tool selection is left to inference.

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