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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so safety is covered. The description adds the step-interpretation rule and the default-list behavior when neither steps nor funnel is given, which is genuinely useful. It says nothing about result shape, limits, or how drop-off is computed (e.g., strict order, time window between steps).

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?

Two sentences, front-loaded with the question the tool answers, then the two input modes. No filler or 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?

For a read-only analytics tool with a 9-parameter, well-documented schema and no output schema, the description covers the essential decisions: step format, step count bounds, and the saved-funnel alternative mode. The main remaining gap is what the response contains, which matters since no output schema exists.

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 89%, so the baseline is 3, and the description adds real meaning on top: the '/' prefix distinguishes page paths from custom event names in steps (the schema documents no item semantics at all), and it clarifies the steps-or-funnel exclusivity. It does not explain breakdown, filters, or period/from interaction.

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 states a specific analysis: counting visits through ordered steps and where they dropped off, plus the page-path vs custom-event rule for steps. It doesn't name any sibling tool for contrast, so it doesn't reach a 5, but the verb and resource are unambiguous.

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?

It gives concrete usage conditions: pass 2-8 steps, or a saved funnel name/id, and omitting both lists saved funnels. That last clause overlaps with list-oriented siblings but is a useful routing hint. It does not explicitly say when not to use it or name an alternative tool for conversion questions.

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