Skip to main content
Glama
Sign In
BoteX

BoteX

by kubainter
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

search_memory

Search the Memory Vault by keyword, tag, or entry kind across local, global, or all scopes to find relevant context, decisions, handoffs, and lessons.

Instructions

Searches the Memory Vault by keyword query, tag, or entry kind
(context, decision, handoff, lesson) across local, global, or all scopes.

Args:
    workspace_dir: Workspace root directory. Empty = engine.default_workspace
           from the config, else the server's current directory.
    query: Free-text search string matched against title, content, and tags.
    tag: Filter by specific tag.
    kind: Filter by entry kind ('context', 'decision', 'handoff', 'lesson').
    scope: Search scope ('local', 'global', or 'all'). Default is 'local'.

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": "search_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNo
kindNo
queryNo
scopeNolocal
workspace_dirNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.2
    • addedInput schema / properties / scope
      Added value: +{
+  "default": "local",
+  "title": "Scope",
+  "type": "string"
+}
  2. Changed1 schema field changedv1.1.1
    • changedInput schema / properties / workspace_dir / default
      Previous value: -"."New value: +""
  3. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose real behavioral detail for scope semantics — 'local', 'global', 'all', plus the default of 'local' — and the workspace_dir fallback chain (config default, then server cwd). However, it never states that the tool is read-only/non-mutating, nor says anything about result limits, ordering, or whether an empty query returns everything.

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?

The behavioural summary is front-loaded in the first sentence before the Args block, so an agent can route on sentence one alone. The Args list is verbose in form but every line carries parameter semantics that the schema omits, so little is wasted.

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 five-parameter, all-optional search tool with an output schema (so return shape needn't be explained) and no annotations, the description covers filters, defaults, and scope resolution adequately. The main omission is result-volume/cap behaviour, which matters because all parameters are optional and an empty call is legal.

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 description coverage is 0%, so the description must compensate, and it largely does: all five parameters are documented with meaning, allowed values, and defaults, and it adds matching semantics not in the schema ('query' matched against title, content, and tags). The remaining gap is that it doesn't say how filters combine — whether query and tag are ANDed or whether scope interacts with workspace_dir.

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?

Opens with a specific verb+resource pair ('Searches the Memory Vault') and immediately enumerates the three ways to narrow results (keyword, tag, kind). The scope vocabulary and entry-kind list make it clearly distinguishable from write-oriented siblings like save_memory, but it never explicitly contrasts itself with read_memory, which returns entry bodies.

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

Usage Guidelines3/5

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

Usage is only implied: the filters suggest 'use this to locate entries', and the entry kinds hint at what you might look for. There is no explicit when-to-use/when-not, and no guidance on how it pairs with siblings (e.g., search here first, then read_memory to fetch the full entry). An agent must infer that selection logic.

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