Run a funnel over a time window and return per-step visitor count, conversion from previous step, conversion from start, and average time to convert between steps. Returns truncated flags if the scan cap was hit.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | Start of window as unix milliseconds. Defaults to 7 days ago. | |
| until | No | End of window as unix milliseconds. Defaults to now. | |
| funnelId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds behavioral context about returning 'truncated' flags if the scan cap is hit, which goes beyond the annotations.
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 concise (two sentences), front-loaded with the main action and outputs, and contains no unnecessary information.
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?
Given 3 parameters and no output schema, the description explains the return values (counts, conversions, time, truncated flag) adequately. Lacks only minor details like pagination.
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 67% (since and until have descriptions, funnelId does not). The description explains the time window concept relating to since/until but does not add meaning for funnelId. Adds some value but not comprehensive.
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 uses a specific verb ('Run a funnel') and resource ('funnel') with clear output details (per-step visitor count, conversions, average time). It distinguishes from sibling tools like create_funnel, delete_funnel, get_funnel.
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 states when to use (run a funnel over a time window) but does not explicitly provide exclusions or alternatives. The context is implied by sibling tool names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
All tools have clearly distinct purposes. Funnel operations (compute, create, delete, get, list, update) are well-separated from event tools (events_count, recent_events) and pageview tools (pageviews_count, top_pages, top_referrers). Composite snapshots (user_activity, weekly_digest) and utility tools (get_usage, list_projects) are unique.
Naming pattern is inconsistent: some tools use verb_noun (compute_funnel, create_funnel), others noun_verb (events_count, pageviews_count), and some are adjective_noun (recent_events, top_pages) or noun_noun (user_activity, weekly_digest). While readable, the lack of a consistent convention reduces predictability.
15 tools is at the upper boundary of 'well-scoped' but still appropriate for an analytics platform. Each tool serves a necessary function without unnecessary duplication, though a few more could be justified.
The tool set covers core analytics operations: CRUD for funnels, event and pageview counting, top pages/referrers, user and weekly snapshots, and project/usage info. Minor gaps exist (e.g., no session-level detail), but overall it addresses common analytics queries well.
