Skip to main content
Glama
Sign In
RMS Memory MCP

RMS Memory MCP

by max-ramas
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

rms_read

Read markdown notes from the RMS Memory vault by relative path, returning the full note by default or token-saving outlines, sections, character windows, and unchanged-content stubs for long notes.

Instructions

Read a markdown document from the RMS Memory vault by relative path (e.g. 'rules/api.md'). Whole note by default. For long notes save tokens: outline (headings with sizes), heading (one section), max_chars/offset (window), if_hash (hash from an earlier read; returns a short 'unchanged' stub if the note has not changed).

Input Schema

NameRequiredDescriptionDefault
idNo
pathYesRelative path to the markdown document in the vault.
offsetNoStart at this character offset (with max_chars).
headingNoReturn only the section under this heading (with its sub-sections). Exact title first, then substring.
if_hashNocontent_hash from an earlier read of this note. If unchanged, a short stub is returned instead of the text.
outlineNoReturn only a table of contents (headings with character sizes, frontmatter summary, content hash).
projectNoProject key (when the client sends no workspace root).
max_charsNoReturn at most this many characters; the reply says which offset continues.
noPromoteNoRead without side effects. Vault reads are already side-effect free; accepted for explicit forward-compatible contracts.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv1.4.3
    • addedInput schema / properties / heading
      Added value: +{
+  "description": "Return only the section under this heading (with its sub-sections). Exact title first, then substring.",
+  "type": "string"
+}
    • addedInput schema / properties / if_hash
      Added value: +{
+  "description": "content_hash from an earlier read of this note. If unchanged, a short stub is returned instead of the text.",
+  "type": "string"
+}
    • addedInput schema / properties / max_chars
      Added value: +{
+  "description": "Return at most this many characters; the reply says which offset continues.",
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "Start at this character offset (with max_chars).",
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / outline
      Added value: +{
+  "description": "Return only a table of contents (headings with character sizes, frontmatter summary, content hash).",
+  "type": "boolean"
+}
    • changedInput schema / properties / project / description
      Previous value: -"Registered project key, used when the MCP client did not provide a workspace root."New value: +"Project key (when the client sends no workspace root)."
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the burden, and it does disclose non-obvious behavior: the default is a whole-note read, outline returns headings with sizes, and if_hash returns a short 'unchanged' stub instead of text. It is silent on failure behavior (nonexistent path, ambiguous heading match) and on whether reads are side-effect free, which the schema hints at only via noPromote.

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, front-loaded with the core purpose and the path example before any optional modes. Parameter names are backticked for scannability and every clause carries information; nothing is padding.

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 9-parameter tool with no annotations and no output schema, the description covers the important decisions: default behavior, token-saving modes, and the caching stub. The remaining gap is the return shape beyond the stub — it never states that the response includes a content_hash that feeds if_hash — and there is no mention of how id relates to path.

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 89%, so the baseline is 3; the description earns above that by explaining what each mode actually yields (outline = headings with sizes, heading = one section, max_chars/offset = window, if_hash = unchanged stub), which the schema descriptions only state tersely. It adds nothing for id, project, or noPromote, but those are already documented in the schema.

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 ('Read a markdown document from the RMS Memory vault') plus the identification scheme ('relative path (e.g. 'rules/api.md')'). The read-by-path framing is unmistakably distinct from siblings like rms_search or rms_code_search without needing to name them.

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?

The second sentence is explicit mode-selection guidance — 'For long notes save tokens' followed by the four escalating options (outline, heading, max_chars/offset, if_hash). What is missing is any guidance on when to pick rms_read over rms_search or rms_code_search, so alternatives are implied rather than stated.

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