static.md

Change agent memory

memory

Destructive

Changes agent memory, markdown files under /memories, with the writing commands of Anthropic's memory tool; memory_view reads it. Each file is a static.md note in the user's /memories folder: /memories/projects/static-md.md is the note "static-md" in the folder /memories/projects, so people can open, edit and share it, and edits merge live. create writes a file, replacing the text of one that exists. str_replace replaces old_str, which must occur exactly once, with new_str. insert puts insert_text after line insert_line (0 for the top). delete removes a file, or a directory with everything in it. rename moves a file or directory from old_path to new_path. File names: up to 32 characters before ".md", of letters A-Z, digits, "-", "_" and "."; directories up to 9 levels. Encrypted notes are refused.

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": {
      "command": "<command>"
    },
    "name": "memory"
  }
}

Input Schema

Name	Required	Description
`path`	No	The file or directory, under /memories (e.g. "/memories/projects/static-md.md"). Every command but rename
`command`	Yes	What to change; view is memory_view
`new_str`	No	str_replace: the replacement (empty or left out deletes old_str)
`old_str`	No	str_replace: the text to replace, exactly as in the file
`new_path`	No	rename: where it goes
`old_path`	No	rename: the file or directory to move
`file_text`	No	create: the whole file
`insert_line`	No	insert: the line to insert after; 0 is the top of the file
`insert_text`	No	insert: the text to insert

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 25, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Adds real context beyond the destructiveHint=true annotation: delete removes a directory 'with everything in it', create overwrites existing text, and encrypted notes are refused. It still omits permission/auth requirements and what happens on validation failure, but the destructive consequences are described rather than merely flagged.

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 and dense, with each command's behavior given one sentence and no filler. Some sentences are long and run together (the static-md note explanation), which slightly hurts scanability but nothing is redundant with the schema.

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 nine-parameter, destructive, multi-mode write tool with no output schema, the description covers every command mode plus naming limits and the encrypted-note refusal. Missing only return/error behavior for the write commands, which is a modest gap given annotations already carry the safety profile.

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 already 100%, so baseline is 3; the description earns above that by specifying that old_str 'must occur exactly once', that insert_line 0 means the top, and by stating the filename/directory-depth constraints (32 chars, 9 levels) that the schema does not encode.

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 ('Changes agent memory, markdown files under /memories') and immediately scopes it to the writing commands, naming memory_view as the reader. An agent can distinguish this from read_note, update_note, or memory_view without opening a schema.

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?

Explicitly routes read operations away ('memory_view reads it'), which is the key alternative among the siblings. It does not spell out when to prefer create vs. str_replace vs. insert beyond the mechanical per-command semantics, so it stops short of full when/when-not guidance.

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

All static.md tools Inspect

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

Need Help?