Skip to main content
Glama

Metadata MCP Connector

by io.metadata.mcp-server
OverviewDiscussionsAdmin

Search Insights Criteria Fields

search_insights_criteria_fields
Read-only

Discover the fields an Insights (Spotlight) account-journey segment can filter on: the exact field names, their type, the operators each accepts, and the picklist options.

USE BEFORE create_segment, and before get_insights_report when you filter it. Omit search_keywords to get the whole catalog in compact form; pass keywords to narrow it (matched against field names and labels: "impressions", "score", "visits", "pricing", "opportunity").

WHAT A SEGMENT FILTERS: the companies in the account's Spotlight journey, one row per company, with engagement metrics that are computed INSIDE the lookback window the audience is later created with (create_audience_from_segment.lookback_window). Needs the Insights (Spotlight) subscription on the account: without it the catalog comes back empty or the call fails, and the right move is to say so, not to guess fields.

STATIC FIELDS (always present; use the NAME in criteria):

  • Marketing touchpoints: LINKEDIN_IMPRESSIONS (NUMERIC), LINKEDIN_ADS_ENGAGEMENT (NUMERIC, LinkedIn clicks), FORM_SUBMISSIONS (NUMERIC), CHANNEL (MULTIPICKLIST: LINKEDIN, FACEBOOK, GOOGLE_ADS, INSTAGRAM, EMAIL, THIRD_PARTY, DIRECT), HIGH_INTENT_PAGES (BOOLEAN)

  • Website engagement: WEBSITE_VISITS, TOTAL_PAGE_VIEWS, UNIQUE_VISITORS (NUMERIC), PAGE_URL (STRING; LIKE "/pricing" is the page-visit filter), IDENTIFIED_VISITORS (BOOLEAN), IS_ABM (BOOLEAN), UTM_SOURCE / UTM_MEDIUM / UTM_CAMPAIGN / UTM_TERM / UTM_CONTENT / UTM_KEYWORD / REFERRER (ARRAY)

  • Engagement score: SCORE (MULTIPICKLIST classification), CONFIDENCE_SCORE and TREND (MULTIPICKLIST)

  • CRM: ACCOUNT_STATUS (opportunity status, MULTIPICKLIST), IN_CRM (BOOLEAN), ACCOUNT_OWNER (MULTIPICKLIST); HubSpot adds DEAL_TYPE and DEAL_STAGE; Salesforce adds EMAILS, CALLS, EVENTS (NUMERIC), CAMPAIGN_NAME, CAMPAIGN_TYPE, CAMPAIGN_MEMBER_STATUS, RESPONDED; any connected CRM adds DYNAMIC fields (criterion field "DYNAMIC" plus entity and property)

  • Firmographic: INDUSTRIES, REVENUES, EMPLOYEES, COUNTRIES (MULTIPICKLIST), COMPANY_DOMAIN, COMPANY_NAME (STRING), ACCOUNT_LIST (MULTIPICKLIST of the account's ABM lists)

RESPONSE: {fields: [{name, label, criteria_fields: [{name, label, type, operators, options (first 10), options_total, dynamic?, entity?, status?}]}], missing_crm_fields, criteria_rules}. criteria_rules restates the value shape per type. A dynamic field with status PENDING is still being extracted from the CRM and cannot be used yet.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
search_keywordsNoOptional keywords matched against field names and labels, e.g. ['impressions', 'score']. Omit for the whole catalog.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already mark the call read-only and non-destructive, and the description adds substantial behavioral context: it requires the Insights (Spotlight) subscription, warns that the catalog can come back empty or the call can fail without it, and explains that dynamic fields with status PENDING are not yet usable. It also discloses the response shape, going well beyond the annotation baseline.

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

Conciseness5/5

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

Although long, the description earns its length: purpose is front-loaded, followed by usage sequencing, subscription prerequisites, a categorized static-field catalog, and response shape. The bullet grouping and section labels make the volume of information scannable and actionable, with no filler.

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?

The tool has only one optional parameter, no output schema, and no enums, so the description carries the full burden. It covers the response contract, field categories, per-field types, operator implications, subscription preconditions, and dynamic-field status. An agent has everything needed to call it correctly and interpret results.

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?

The schema already describes search_keywords as 'Optional keywords matched against field names and labels, e.g. ['impressions', 'score']. Omit for the whole catalog,' and the description largely restates this. With 100% schema description coverage, the baseline is 3, and the description adds no material new meaning about the parameter.

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 specific verb and resource: 'Discover the fields an Insights (Spotlight) account-journey segment can filter on.' It names exactly what the tool returns (field names, types, operators, picklist options) and distinguishes it from siblings like get_insights_report and create_segment. The scope is unmistakable.

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?

The description explicitly says 'USE BEFORE create_segment, and before get_insights_report when you filter it,' giving concrete sequencing guidance. It also explains when to omit vs. pass search_keywords and instructs the agent to say the subscription is missing rather than guess fields. This is exemplary usage guidance.

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

All Metadata MCP Connector 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