Skip to main content
Glama

Segment Domains

segment-domains

Use when the user wants to categorize, group, or understand the composition of a domain list — e.g., "what types of companies did I discover?" AI-driven clustering with auto-generated segment labels.

Groups similar domains together and generates descriptive segment names. Returns results inline and attempts to save non-empty results to the account for later access from the Tasks tab. Saving may fail without affecting the inline results. May take longer for large lists.

Domains: comma-separated string, optionally unioned with query_id. Requires 10-500 domains per MCP call.

Default fields returned: domain, name, segment_description, probability. Use the 'fields' parameter to customize output or set fields=["all"] for full data.

Available segment-specific fields: domain, name, status, score, start_date, end_date, address, latitude, longitude, geo_precision, phones, public_emails, domain_associations, social_urls, redirect_domain, description, keywords, industry_groups, sub_industry, employees, revenue_range, business_model, update_date, mx_provider, linkup, segment_id, segment_description, probability. Field details: https://docs.discolike.com. score: Digital footprint score derived from certificate history (1-800); not a verified measure of company size or buying power start_date: First observed certificate date (YYYY-MM-DD); not a verified company founding or incorporation date

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": {
      "filters": "<filters>"
    },
    "name": "segment-domains"
  }
}

Input Schema

NameRequiredDescriptionDefault
fieldsNoOutput fields to include in response
formatNoResponse formatrows
contextNoWhy you are calling this tool, in a few words. No names or emails.
filtersYesInput filters for the segment-domains MCP tool.
llm_modelNoYour model id, or "unknown".
conversation_idNoThe conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.

Output Schema

NameRequiredDescriptionDefault
_mcp_instructionsNoServer-issued metadata for this conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / conversation_id
      Added value: +{
      +  "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.",
      +  "type": "string"
      +}
    • addedOutput schema / properties
      Added value: +{
      +  "_mcp_instructions": {
      +    "description": "Server-issued metadata for this conversation.",
      +    "properties": {
      +      "conversation_id": {
      +        "description": "The server-issued conversation identifier.",
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  }
      +}
  2. Changed2 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Why you are calling this tool, in a few words. No names or emails.",
      +  "type": "string"
      +}
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "Your model id, or \"unknown\".",
      +  "type": "string"
      +}
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations, the description discloses real behavioral traits: results are returned inline, a copy is also persisted to the account (Tasks tab), persistence can fail without affecting inline results, and latency grows with list size. That side-effect and failure-mode disclosure is exactly what the annotations (readOnlyHint=false, destructiveHint=false) do not convey. Auth requirements and rate limits are still unstated.

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 trigger sentence and the behavioral paragraph are well front-loaded and earn their space. However, the 30-plus-item field enumeration is a wall of text that duplicates a linked docs URL and dilutes the signal, and the two trailing field caveats are tacked on after the enumeration rather than grouped with it.

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?

For a six-parameter tool with a nested filters object and an output schema, the description covers preconditions, persistence side effects, latency, and field customization, which is enough to call it correctly. The main residual gap is the query_id/max_segments interaction, which is left to the schema.

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

Parameters5/5

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

Schema coverage is already 100%, so the baseline is 3, but the description adds material meaning: domains is optionally unioned with query_id, the 10-500 count constraint (absent from the schema), the default output field set, the fields=["all"] shorthand, and caveats that score and start_date are not verified business measures. That is genuine semantic value over the schema.

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?

The description gives a specific verb set (categorize, group, understand composition) against a specific resource (a domain list) and adds a concrete user-intent example ("what types of companies did I discover?"), plus the mechanism (AI-driven clustering with auto-generated segment labels). It never names a sibling such as get-domains-by-tags or crm-writeback-segments to draw a boundary, so it falls short of a 5.

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?

The opening "Use when the user wants to categorize, group, or understand the composition of a domain list" is an explicit trigger condition, and "Requires 10-500 domains per MCP call" sets a hard precondition an agent must check before calling. There is no when-not guidance or named alternative for cases where clustering is the wrong 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