Skip to main content
Glama
admin0330

KnowledgeBase MCP

by admin0330

kb_reindex

Updates the search index by scanning the whole drive, useful after bulk file copies or for a full rebuild. Runs in the background and returns progress.

Instructions

Scan the whole drive and bring the search index up to date.

Rarely needed: added/imported/moved files are indexed immediately, and a catch-up scan runs by itself whenever the drive is plugged in. Use it after copying many files onto the drive with Finder, or with full=True to rebuild. Runs in the background; this call waits up to wait_seconds (0-50) and otherwise returns progress -- follow it with kb_status.

:param full: When true, re-extract every file instead of only changed ones. :param wait_seconds: How long to wait for completion before returning.

Input Schema

NameRequiredDescriptionDefault
fullNo
wait_secondsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does disclose key traits: it runs in the background, blocks for at most wait_seconds, and may return progress rather than a finished result. It does not state cost/duration expectations for a full rebuild, whether the call is safe to interrupt or run concurrently, or whether the index is left inconsistent if aborted.

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 the action, then when-to-use, then runtime behavior, then params — a sensible order. Minor waste: the wait_seconds explanation in the body is repeated almost verbatim in the :param line.

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?

An output schema exists, so return-value shape need not be described, and the description still covers the one return nuance that matters — it may return partial progress. When-to-use, async behavior, follow-up tool, and both parameters are all addressed for a 2-param optional-args tool.

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 0%, so the description must compensate, and it largely does: `full` is explained as re-extracting every file vs only changed ones, and `wait_seconds` is explained plus given the 0-50 range that the schema lacks. It omits the documented defaults (false / 40) and does not say what happens if wait_seconds is exceeded beyond 'returns progress'.

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 — 'Scan the whole drive and bring the search index up to date' — which is clearly distinct from siblings like kb_scan_inbox (inbox only), kb_status (read progress), and kb_search (query). An agent can route to it without opening the schema.

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 says it is 'Rarely needed' because imported/moved files index immediately and a catch-up scan runs on plug-in, then names the two conditions that do warrant it (bulk Finder copy, full=True rebuild). It also routes to kb_status as the follow-up tool for the progress case.

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