Skip to main content
Glama

DeskCrew - AI Chatbot, Helpdesk & Knowledge base

by io.deskcrew
OverviewDiscussionsAdmin

search_kb

Read-only full-text search over this tenant’s PUBLISHED knowledge-base articles (playbooks, policies, how-tos); unpublished drafts are never returned and the tenant is fixed by your credentials. Reach for this FIRST to ground an answer in official, tenant-specific guidance before replying to a customer or drafting a resolution. Returns articles ranked by relevance, each with its id, title, a highlighted snippet, and updatedAt: search uses AND semantics, so every word in the query must match. [free]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoOptional. Maximum number of ranked articles to return, 1 to 20. Defaults to 10 when omitted. A number sent as a string is read as a number, and anything above 20 is treated as 20.
queryYesThe search phrase. Uses AND full-text semantics: EVERY word must appear in an article to match, so keep it to the key terms (e.g. "refund policy" or "reset password"), not a full sentence. Comes from the user's question or the topic you need to ground your answer in.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Optional. Maximum number of ranked articles to return, 1–20. Defaults to 10 when omitted."New value: +"Optional. Maximum number of ranked articles to return, 1 to 20. Defaults to 10 when omitted. A number sent as a string is read as a number, and anything above 20 is treated as 20."
  2. Changed1 schema field changed
    • changedInput schema / properties / query / description
      Previous value: -"The search phrase. Uses AND full-text semantics — EVERY word must appear in an article to match, so keep it to the key terms (e.g. \"refund policy\" or \"reset password\"), not a full sentence. Comes from the user's question or the topic you need to ground your answer in."New value: +"The search phrase. Uses AND full-text semantics: EVERY word must appear in an article to match, so keep it to the key terms (e.g. \"refund policy\" or \"reset password\"), not a full sentence. Comes from the user's question or the topic you need to ground your answer in."
  3. Changed2 schema fields changed
    • addedInput schema / properties / limit / description
      Added value: +"Optional. Maximum number of ranked articles to return, 1–20. Defaults to 10 when omitted."
    • addedInput schema / properties / query / description
      Added value: +"The search phrase. Uses AND full-text semantics — EVERY word must appear in an article to match, so keep it to the key terms (e.g. \"refund policy\" or \"reset password\"), not a full sentence. Comes from the user's question or the topic you need to ground your answer in."
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers: read-only nature, published-only visibility ('unpublished drafts are never returned'), tenant scoping, ranking behavior, field-level return contents, and AND query semantics. All of these are behavioral facts an agent needs and none are derivable from the schema.

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?

Front-loaded with scope and use case, then behavior, then return shape; the density is high but each clause earns its place. Slightly information-dense in a single paragraph, but 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?

For a read-only search with no output schema, the description covers visibility scope, tenant binding, ranking, return fields, AND semantics, and practical usage positioning relative to adjacent tools. Nothing material is left for the agent to infer.

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 the schema already documents both parameters; the description adds marginal value by restating the AND semantics and reinforcing the practical guidance of using short key terms. This is above the baseline of 3 because of the actionable query-construction advice, but it is largely duplicative of schema content.

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: 'full-text search over PUBLISHED knowledge-base articles', with scope (tenant-fixed, published-only) that clearly separates it from the sibling read_kb and from search_tickets.

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?

Explicitly tells the agent to 'Reach for this FIRST to ground an answer... before replying to a customer or drafting a resolution', naming both the triggering scenario and the alternative workflow, which is stronger guidance than most well-described tools provide.

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

All DeskCrew - AI Chatbot, Helpdesk & Knowledge base toolsInspect
Try in Browser
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources