Skip to main content
Glama

fluent_explain

Read-only

Fetches live ServiceNow SDK Fluent API documentation, signatures, guides, and examples via topic or fuzzy keyword search; supports listing topics and brief previews.

Instructions

Live ServiceNow SDK documentation from now-sdk explain: current Fluent API signatures, guides and examples (about 300 topics), not training-data guesses. Fuzzy search is supported, so a keyword like "catalog variable" works. Use list=true to list topics, peek=true for a short summary. Known topics include: GlideQuery, table API, scoped app, now.config.json, keys.ts, metadata, Table, Record, List, ChoiceSet, Property, Role, Acl, CrossScopePrivilege, ApplicationMenu, Now.del, Now.attach, DataLookup, DatabaseView, BusinessRule, ClientScript, ScriptInclude, ScriptAction, UiAction, UiPolicy, UiPage, UiMacro, DataPolicy, Form, StateModel, override, CatalogItem, CatalogItemRecordProducer, VariableSet, CatalogClientScript, CatalogUiPolicy, UserCriteria, RestApi, GraphQLApi, RestMessage, Alias, AliasTemplate, RetryPolicy, ImportSet, InboundEmailAction, Flow, Subflow, Action, CustomAction, TryCatch, DoInParallel, FlowStages, Playbook, ScheduledScript, Sla, EmailNotification, AiAgent, AiAgenticWorkflow, roleMap, NowAssistSkillConfig, ServicePortal, SPWidget, SPPage, SPTheme, SPMenu, SPHeaderFooter, Workspace, Dashboard, Test, TestSuite, InstanceScan, Assessment, RiskAssessment, cicd.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "fluent_explain"
  }
}

Input Schema

NameRequiredDescriptionDefault
listNoList matching topic names instead of showing a document
peekNoShow a brief summary instead of the full document
rangeNoRanked results to show for a fuzzy search, e.g. "5" or "3-7"
topicNoTopic name or keyword. Optional when list=true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv5.0.1
    • addedInput schema / properties / list
      Added value: +{
      +  "description": "List matching topic names instead of showing a document",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / peek
      Added value: +{
      +  "description": "Show a brief summary instead of the full document",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / range
      Added value: +{
      +  "description": "Ranked results to show for a fuzzy search, e.g. \"5\" or \"3-7\"",
      +  "type": "string"
      +}
    • changedInput schema / properties / topic / description
      Previous value: -"Topic to explain. Examples: GlideQuery, table API, scoped app, now.config.json, keys.ts, metadata, Record, Now.del, etc."New value: +"Topic name or keyword. Optional when list=true."
    • changedInput schema / required
      Previous value: -[
      -  "topic"
      -]New value: +[]
  2. Addedv4.9.0

TDQS

A4/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description adds useful behavior context by framing results as live SDK docs rather than model memory, and by disclosing that topic matching is fuzzy. It does not describe result size, truncation, or what happens on an unknown topic, which matters for a search tool with no output schema.

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 opening sentences are well front-loaded and waste nothing, but the inline enumeration of ~80 topic names dominates the description and reads as an unformatted dump. That list has discovery value, yet its length crowds out more important behavioral notes such as defaults and error handling.

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 4-parameter, zero-required, read-only lookup tool with no output schema, the description covers the main modes (list, peek, fuzzy search) well enough to call correctly. Remaining gaps are what happens with no arguments at all and how large the returned documents are.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description goes beyond the schema by explaining that `topic` accepts fuzzy keywords and by enumerating roughly 80 valid topic names (GlideQuery, CatalogItem, SPWidget, etc.), which directly helps pick values. The `range` parameter is left unmentioned in the description, a minor gap.

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 and resource: live ServiceNow SDK documentation served from `now-sdk explain`, with current Fluent API signatures and examples. It explicitly contrasts itself with 'training-data guesses' and enumerates the topic space, so an agent can tell it apart from sibling tools like fluent_sdk_query or fluent_build without opening a 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?

Gives concrete invocation guidance: `list=true` to browse topics, `peek=true` for a short summary, and fuzzy keyword matching such as "catalog variable". It does not, however, explicitly name a sibling alternative or say when-not to use this tool versus the other fluent_* query tools, so it stops short of full routing guidance.

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