Scribe Mail

List identified visitors

list_visitors

Read-onlyIdempotent

The workspace's identified visitors — the customer's own end-users, described by their identify calls (NOT Scribe members/teammates). Each row: distinct_id, traits (PII lives here), first/last_seen_at, and first_touch (the signature click that drove their first visit). Filter by distinct_id (exact), a trait (trait_key + trait_value, e.g. plan=enterprise), identified_via, and first-seen date range. Newest first, paginated.

Input Schema

Name	Required	Description
`page`	No	1-based page (default 1).
`limit`	No	Page size, 1–100 (default 50).
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`end_date`	No	Only visitors first seen on/before this ISO date.
`max_pages`	No	Page cap when auto_paginate is true (default 5).
`trait_key`	No	Segment by a trait: the trait name (e.g. `plan`). Use with `trait_value`.
`start_date`	No	Only visitors first seen on/after this ISO date.
`distinct_id`	No	Find a visitor by their exact user id (distinct_id).
`trait_value`	No	The trait value to match (e.g. `enterprise`).
`auto_paginate`	No	Fetch multiple pages up to `max_pages` (default false).
`identified_via`	No	Filter by acquisition channel: `browser` or `api`.

Output Schema

Name	Required	Description
`data`	Yes
`truncated`	Yes	True when auto_paginate stopped at max_pages with more results remaining.
`pagination`	Yes
`pages_fetched`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 28, 2026
- removedOutput schema / properties / data / items / properties / first_touch / properties / click_id / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / data / items / properties / first_touch / properties / click_id / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / data / items / properties / first_touch / properties / email_id / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / data / items / properties / first_touch / properties / email_id / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / data / items / properties / first_touch / properties / signature_template_id / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / data / items / properties / first_touch / properties / signature_template_id / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / data / items / properties / first_touch / properties / teammate_id / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / data / items / properties / first_touch / properties / teammate_id / type
```
Added value: +[
+  "string",
+  "null"
+]
```
First observedOct 16, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, so the description rightly doesn't restate safety. It adds real context instead: PII lives in traits, results are newest-first, and results are paginated — behaviorally useful for planning queries, though it doesn't mention cost or rate limits on auto_paginate sweeps.

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?

Three tight sentences, front-loaded with the definition and disambiguation before returning to row shape and filters. Dense but no sentence is filler; the parentheticals earn their place by preventing the teammate/end-user confusion.

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

Completeness4/5

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

An output schema exists, so return values needn't be explained, yet the description gives a useful preview of the row shape (distinct_id, traits, first/last_seen_at, first_touch). Adequate for an 11-param listing tool; only the auto_paginate/max_pages interaction is left entirely to the schema.

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

Parameters3/5

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

Schema coverage is 100%, so all 11 parameters are already documented, and the description's filter summary (distinct_id exact, trait_key+trait_value with `plan=enterprise`, identified_via, date range) largely mirrors what the schema says, including the same example values. Baseline 3 applies since the schema carries the parameter burden.

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

Purpose5/5

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

States a specific verb+resource (list the workspace's identified visitors) and immediately disambiguates the concept: end-users from `identify` calls, explicitly NOT Scribe members/teammates. This distinguishes it from list_teammates and from the singular get_visitor without the agent needing to open any schema.

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?

Clear implied context (browse/segment the visitor population) and it enumerates the available filter dimensions, which tells the agent when this tool fits. It does not explicitly route to alternatives such as get_visitor for a single visitor or get_visitor_breakdown for aggregates, so the when-not guidance is missing.

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

All Scribe Mail tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.