Skip to main content
Glama

ai_search

Read-only

Search ServiceNow knowledge bases, service catalogs, and incidents using natural language queries to find relevant records and answers.

Instructions

Semantic AI-powered search across KB, catalog, incidents (ServiceNow AI Search)

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": {
      "query": "<query>"
    },
    "name": "ai_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax results (default: 10)
queryYesNatural language search query
sourcesNoSources to search: ["kb", "catalog", "incident"] (default: all)
search_appNoOptional AI Search application (sys_search_context_config) name or sys_id. Default: Service Portal Default Search Application

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv5.0.1
    • addedInput schema / properties / search_app
      Added value: +{
      +  "description": "Optional AI Search application (sys_search_context_config) name or sys_id. Default: Service Portal Default Search Application",
      +  "type": "string"
      +}
  2. First observedv1.0.2

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and external-reach are covered. The description adds one piece of real behavior beyond that: results are ranked semantically rather than by keyword, which affects result expectations. It says nothing about ranking quality, latency, or result shape.

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?

A single front-loaded sentence with no filler; the purpose and scope arrive immediately. The trailing parenthetical naming the underlying ServiceNow feature is the only marginally expendable element.

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

Completeness3/5

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

For a four-parameter read-only search with full schema coverage and annotations, the description is adequate but thin. It does not explain result content or how results differ from the keyword-oriented search siblings, which is the main ambiguity an agent faces when choosing this tool.

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 all four parameters including sources, limit, and search_app are already documented in the schema. The description only restates the source list that the schema's sources parameter already enumerates, adding no extra syntax or constraint detail. Baseline 3 applies.

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 ('search') and a concrete resource set ('KB, catalog, incidents') with a qualifier ('Semantic AI-powered'), so an agent knows exactly what is searched. It stops short of distinguishing this from siblings such as search_knowledge, search_catalog, or natural_language_search, leaving overlap unresolved.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, and no alternative is named. The only implicit signal is the source list, which hints at scope but does not tell an agent why it should pick this over the several keyword/semantic search siblings.

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

Deploy Server

Other Tools