Skip to main content
Glama
CROW: LLM Wiki

CROW: LLM Wiki

Official

sync_folder

Files every readable document in a folder into the Markdown wiki and keeps memory aligned, using later runs to process only new or changed files while marking removed ones.

Instructions

File every document of a folder on this computer and keep the memory in step with it.

Call it when the user asks to import or update a whole folder; for one file use remember_file. The first call files every readable document; a later call files only the new and changed ones, with no model call for the rest. A file removed from the folder is marked as removed, and its notes stay. Returns counts (created, merged, unchanged, removed, skipped) and the errors. With your models, it returns a job with requests instead: answer them with reply.

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": {
      "folder": "<folder>"
    },
    "name": "sync_folder"
  }
}

Input Schema

NameRequiredDescriptionDefault
folderYesA folder on this computer whose documents to file

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.4

TDQS

A4.4/5.0
Behavior4/5

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

Goes well beyond the annotations: incremental behaviour (only new/changed files, no model call for the rest), removal semantics (marked removed, notes preserved), and the model-mediated branch that returns a `job` to be answered with `reply`. That job/reply handoff is the key behavioural detail an agent would otherwise miss; the only minor gap is that permissions or size/time limits on a large folder are not mentioned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads purpose, then routing, then behavioural details, with no filler sentences. Each sentence contributes a distinct fact an agent needs (scope, alternative, incremental behaviour, removal policy, return shape, follow-up action).

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?

An output schema exists, so the description need not dwell on return values, yet it still summarises counts/errors and flags the alternate `job` response that drives a follow-up `reply` call. Complete enough to invoke correctly; only edge conditions on very large or unreadable folders are left implicit.

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 coverage is 100% and the single `folder` parameter already documents that it is a folder on this computer, so the description adds little parameter-level meaning. Baseline 3 is appropriate when the schema carries the burden.

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 — "File every document of a folder on this computer" — plus the memory-sync side effect. It also names the sibling it is not (`remember_file`), so an agent can separate the bulk case from the single-file case without opening either 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?

Gives an explicit trigger ("when the user asks to import or update a whole folder") and an explicit exclusion with the alternative to use instead ("for one file use `remember_file`"). It also distinguishes first call vs. later calls, which is a usage decision the agent must make.

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