Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Crm segments

crm_segments
Read-only

Counts the business's contacts (the People place's relationships): the total, by kind (person, org, outlet, creator, customer, subscriber, prospect) and by stage (unknown, aware, contacted, replied, engaged, converted, churned, declined), how many may not be contacted now (suppressed), and the touches of the last days: total, out and in, by channel and by kind (pitch, email, reply, dm, order, sign-up and the rest). Use it for the shape of the relationships; to find someone use crm_search, for one person's history crm_timeline.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "days": "<days>"
    },
    "name": "crm_segments"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysYesThe span for the touches, in days back from now; the contact counts are always all of them.
projectNoThe project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered; the description adds real behavioral content by disclosing that contact counts are all-time while only touches are windowed, and that suppression is a distinct slice. It stops short of stating response shape or size limits for the aggregate output, but with annotations carrying the safety profile that is a minor omission.

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

Conciseness3/5

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

The verb and subject are front-loaded, which is good, but the body is a single sprawling sentence with stacked parentheticals listing seven kinds, eight stages, and seven touch types. Those enumerations do convey what gets returned, yet the density makes it hard to scan and some of the itemized vocabulary is more verbose than the agent needs to select the tool.

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?

There is no output schema, so the description has to carry the return semantics itself — and it does, naming every aggregation dimension (totals, kind, stage, suppressed, touch direction, channel, touch kind). For a read-only two-parameter reporting tool that is nearly complete; only pagination or output size behavior is left unstated.

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 description coverage is 100%, so both 'days' and 'project' are already documented — including the same nuance that contact counts ignore the span. The description's phrasing about 'the touches of the last days' reinforces that relationship but adds no format, boundary, or default information beyond the schema, so the baseline 3 applies.

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?

The description opens with a concrete verb and resource ('Counts the business's contacts') and then enumerates exactly what gets counted — totals, by kind, by stage, suppressed, and recent touches. It also names the two things it is not (crm_search for finding someone, crm_timeline for one person's history), so an agent can distinguish it from siblings without opening any other definition.

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

Usage Guidelines5/5

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

It states the intended use case explicitly ('Use it for the shape of the relationships') and routes the agent to the correct alternatives with their conditions ('to find someone use crm_search, for one person's history crm_timeline'). The when-to-use and which-sibling split is fully spelled out rather than implied.

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

All Marsell toolsInspect
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.

Resources