Skip to main content
Glama

User paths

get_flow
Read-onlyIdempotent

What visits did next, as a tree up to 4 steps deep from a starting node (default: where visits enter the site). Every count is conditioned on the whole path above it, so it can be read as a journey. Each box lists its top branches plus 'other', 'rare' and 'exit' rows that sum to its visits. Boxes with below_threshold set are too thin to interpret: say so. Expand a branch by passing its key in path; find a root with find_flow_nodes. Dates are the project's calendar days, YYYY-MM-DD (timezone: get_project); timestamps are UTC. Omit from/to for the last 28 complete days, ending yesterday.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_flow"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoLast day, YYYY-MM-DD in the project's timezone, inclusive. Default: yesterday, the last complete day.
fromNoFirst day, YYYY-MM-DD in the project's timezone, inclusive. Default: 27 days before 'to'.
pathNoComma-separated node keys (the 'key' of branches, copied as returned) naming the branch to expand below the root, outermost first, at most 3. Keys are encoded as for root, e.g. pageview:https%3A%2F%2Fshop.acme.com:%2Fcart:,click:https%3A%2F%2Fshop.acme.com:%2Fcart:checkout.
rootNoNode key to start from, exactly as returned by find_flow_nodes: event_type:page_origin:page_path:feature_name, four segments, each percent-encoded so a colon or slash inside one is %3A or %2F. The page view of https://shop.acme.com/ is pageview:https%3A%2F%2Fshop.acme.com:%2F: (never pageview:https://shop.acme.com/), a click on add-to-cart on /products/:id is click:https%3A%2F%2Fshop.acme.com:%2Fproducts%2F%3Aid:add-to-cart. Default: where visits enter.
levelNosteps (default): pages plus named features. pages: pageviews only.
projectNoProject ID, from list_projects. Required when this connection covers more than one project; may be left out when it covers one (and with an API key, which belongs to one project).
branchesNoReal branches returned per box, 1-20. Default 6.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / path / description
      Previous value: -"Comma-separated node keys (the 'key' of branches) naming the branch to expand below the root, outermost first, at most 3."New value: +"Comma-separated node keys (the 'key' of branches, copied as returned) naming the branch to expand below the root, outermost first, at most 3. Keys are encoded as for root, e.g. pageview:https%3A%2F%2Fshop.acme.com:%2Fcart:,click:https%3A%2F%2Fshop.acme.com:%2Fcart:checkout."
    • changedInput schema / properties / root / description
      Previous value: -"Node key to start from, exactly as returned by find_flow_nodes. Default: where visits enter."New value: +"Node key to start from, exactly as returned by find_flow_nodes: event_type:page_origin:page_path:feature_name, four segments, each percent-encoded so a colon or slash inside one is %3A or %2F. The page view of https://shop.acme.com/ is pageview:https%3A%2F%2Fshop.acme.com:%2F: (never pageview:https://shop.acme.com/), a click on add-to-cart on /products/:id is click:https%3A%2F%2Fshop.acme.com:%2Fproducts%2F%3Aid:add-to-cart. Default: where visits enter."
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the read-only, idempotent safety profile, and the description adds real semantics beyond that: counts are conditional on the path above, each box's rows sum to its visits, and thin boxes marked below_threshold should be reported as such. The note that it is a tree limited to 4 steps is a useful behavioral constraint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads what the tool returns, then moves to interpretation rules, then expansion workflow, then date semantics; every sentence carries information. The text is dense rather than bloated, though the below_threshold reference appears without any prior grounding in the input schema, which can briefly read as unfamiliar jargon.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of explaining the return shape, and it does: a tree of boxes with counts conditioned on ancestry, top branches plus 'other', 'rare' and 'exit' rows that sum to box visits. Combined with the defaulting and expansion guidance, an agent has enough to call this and interpret the result without further lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above that by tying parameters together into a workflow (root comes from find_flow_nodes, path names the branch to expand, from/to default to the last 28 complete days ending yesterday). It also clarifies that dates are calendar days in the project timezone while timestamps are UTC, which the schema only implies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'What visits did next, as a tree up to 4 steps deep from a starting node', which pins down the output shape and depth. It distinguishes itself implicitly from funnel/dashboard siblings through the tree-of-journeys framing, but never names or contrasts an alternative tool directly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete operating guidance: expand a branch by passing its key in path, find a root with find_flow_nodes, omit from/to for the last 28 complete days. It is missing explicit when-not-to-use guidance, such as when a funnel or overview query would be the better choice.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources