Skip to main content
Glama
CROW: LLM Wiki

CROW: LLM Wiki

Official

remember_file

Files or imports a document from disk—text, Markdown, PDF, Word, PowerPoint, Excel, or OpenDocument—into a Markdown wiki memory, adding or merging notes without deleting.

Instructions

File a document from this computer's disk: text, Markdown, PDF, Word, PowerPoint, Excel or OpenDocument.

Call it when the user asks to add, import or file a file; for a whole folder use sync_folder, for something said in chat remember. Its text is filed as remember files a text, a spreadsheet one note per sheet, and the file's path is kept as the source. Returns {action, note, folder, related}. Adds or merges, never deletes. An unknown path returns an error. 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": {
      "path": "<path>"
    },
    "name": "remember_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesThe document's path on this computer: text, Markdown, PDF, Office…
titleNoA title; empty: the file's name

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.4

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses that the operation "adds or merges, never deletes," that the file's path is retained as the source, that a spreadsheet becomes one note per sheet, that an unknown path returns an error, and that some model configurations return a `job` whose requests must be answered with `reply`. That is substantive behavioral context the annotations alone do not convey.

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?

Information is front-loaded — action first, then trigger, then alternatives, then return/edge behavior. A few clauses are awkwardly compressed ("Its text is filed as `remember` files a text"), costing some readability, but almost every sentence carries load.

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 2-parameter ingestion tool it covers the trigger, format scope, provenance, destructive-behavior boundary, error case, and the asynchronous job branch. An output schema exists, yet the description still names the response keys, which is helpful rather than redundant.

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 description coverage is 100%, and the schema already documents `path` and `title` (including the default of the file's name). The description adds little parameter-specific meaning beyond noting formats accepted at the path; the "kept as the source" remark concerns provenance/return behavior rather than the parameter itself. Baseline 3 applies when the schema carries the load.

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?

"File a document from this computer's disk" gives a specific verb and resource, then enumerates the supported formats (text, Markdown, PDF, Word, PowerPoint, Excel, OpenDocument). It explicitly contrasts with `sync_folder` (whole folder) and `remember` (chat text), so an agent can distinguish it from siblings without opening any 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?

It states the triggering condition ("when the user asks to add, import or file a file") and routes to the correct alternatives: `sync_folder` for folders, `remember` for chat content, `reply` for the job-request flow. Explicit when-to-use plus named alternatives is the top band.

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