Skip to main content
Glama
Sign In

OwlMem

by com.owlmem
OverviewDiscussionsAdmin

kb_write

Destructive

Write a document to your team's knowledge base; every AI in the team sees it. Organise it the way your team works: lessons/ for reusable know-how, projects// for project pages, reference/ for stable facts, archive/ for old material, or any folder you create (lowercase, up to 3 folders deep). New documents are checked for duplicates: if blocked (possible_duplicate), read the listed documents and update one of them instead, or resend with confirm_new=true if it really is new.

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>",
      "content": "<content>"
    },
    "name": "kb_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNocreate (new file), update (replace the whole file) or append (add to the end)create
pathYes<folder>/<name>.md or <folder>/<sub>/<name>.md, e.g. lessons/deploy/feedback_migrations.md
contentYesFull Markdown with YAML front matter (name, description)
messageNoCommit message
confirm_newNoSet true after checking it is not a duplicate

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety bar is partly met. The description adds behavior the annotations cannot express: writes are team-wide visible, new documents pass through a duplicate gate, and a blocked write returns a possible_duplicate signal with a defined confirmation path. It does not spell out that update mode replaces the whole file, but the schema covers that.

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?

Two sentences, both front-loaded with the highest-value information: what the tool does and who sees it, then how to organize and how to recover from a duplicate block. No filler and no repetition of the field names.

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?

With 5 parameters, no output schema, and a destructive write, the description covers visibility, organization conventions, and the duplicate/confirmation loop—enough for correct invocation. It leaves the agent guessing about the success return shape, but with no output schema that is a minor omission rather than a blocker.

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 baseline is 3, and the description exceeds it by adding path semantics (lowercase, max 3 folders deep, recommended folder taxonomy) and by explaining the operational trigger for confirm_new. Mode enum values are left entirely to the schema, which is acceptable given full coverage.

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 and resource ("Write a document to your team's knowledge base") plus the crucial audience scope ("every AI in the team sees it"), which cleanly separates it from read-side siblings like kb_read and kb_search. It stops short of naming the nearest write-side alternative (kb_retain), so the differentiation is strong but not exhaustive.

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

Usage Guidelines4/5

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

Gives concrete routing advice via the folder taxonomy (lessons/, projects/<project>/, reference/, archive/) and prescribes the exact recovery path when a write is blocked: read the listed documents and update one, or resend with confirm_new=true. There is no explicit exclusion telling the agent when NOT to use this tool versus kb_retain or kb_move, which keeps it out of 5 territory.

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

All OwlMem toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources