Funnel subjects

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds real value: ordering (newest first), pagination via cursor ('a page at a time'), timestamp format with UTC offsets and the fallback to +00:00, the 400-day range cap, and the caveat that reported values are raw text sent by visitors. Only the shape of returned records is left unstated.

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 purpose and ordering come first, followed by timezone/range rules and a data-provenance note; nearly every clause carries information. The opening sentence is an awkward run-on ('who reached one funnel step, or who reached the step before it and never this one'), costing a bit of clarity, but there is no filler.

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 an 8-parameter, read-only analysis tool with no output schema, the description covers ordering, pagination, timezone handling, date bounds, and data trustworthiness. The main remaining gap is that it never indicates what fields identify each returned subject, which an agent would need to know to use the response.

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 baseline is 3, but the description adds constraints the schema does not state: dates are interpreted in the project time zone, to may not exceed the project's today, a range spans at most 400 days, and the project id's source is list_projects. These are substantive semantics beyond the field-level descriptions.

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 verb+resource: it returns the visits or identified people that reached a given funnel step, or dropped before it, newest first and paginated. That is far more than a restatement of the title. It does not, however, explicitly distinguish itself from sibling tools like funnel or funnel_segments, which likely return aggregated counts.

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?

Usage is implied through the reached/dropped outcome and the 'one funnel step' framing, and it helpfully notes that project_id and the project's today come from list_projects. But there is no explicit statement of when to choose this over funnel/funnel_segments, nor any stated exclusions or prerequisites beyond that pointer.

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