Funnel segments

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely useful operational context: the project's today comes from list_projects, ranges cap at 400 days, `to` cannot exceed today, and the reported text is raw visitor-supplied data. The segments summing to the whole funnel is a real semantic guarantee not present in the schema.

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?

Three sentences, front-loaded with the tool's core semantics before the boilerplate date/privacy caveats. The date sentence duplicates schema constraints, but the 400-day cap and timezone framing are new information and earn their place.

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 query with no output schema, the definition supplies everything an agent needs before calling: how the funnel is segmented, where project_id and today come from, the date window limits, and a data-quality caveat about raw text values.

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 description coverage is 100%, so every parameter is already documented, including `by`'s device/channel enum and the 2-8 step limits. The description largely restates the date and timezone rules already in the schema and adds no per-parameter meaning, so the baseline 3 applies.

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 the resource (a funnel) and its distinguishing dimension (per device type or per channel of the visit), which implicitly separates it from the unsegmented `funnel` and from `funnel_subjects`. It does not name those siblings explicitly, so an agent must infer the contrast rather than read it.

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 — pick this when you want the funnel broken down by device or channel — but there is no explicit when-to-use statement, no when-not to use it, and no pointer to `funnel` or `funnel_subjects` as the alternative for a single whole-funnel figure.

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