Skip to main content
Glama
anchor-notes-mcp

anchor-notes-mcp

by NatanaelJose

update_note

Edit an existing note by replacing its markdown body, title, tags, reminder, background, or archive state with a required version check. Send the complete edited body because content overwrites it.

Instructions

Change a note. content replaces the whole body, so read the note with get_note first and send the full edited markdown. To only add text at the end, use append_to_note instead.

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": {
      "id": "<id>",
      "baseVersion": "<baseVersion>"
    },
    "name": "update_note"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
titleNo
tagIdsNoReplaces the note's tags
contentNoMarkdown. Supported: # headings (1-3), **bold**, *italic*, <u>underline</u>, ~~strike~~, ==highlight==, [links](url), - bullets, 1. numbered, - [ ] / - [x] checklists (nest with 4 spaces), > quotes, ``` code blocks.
isPinnedNo
reminderNoReminder; null removes it
backgroundNoNote background; null clears it
isArchivedNo
baseVersionYes`version` from the get_note you based this edit on

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: `content` is a whole-body replacement, which is the main footgun, plus the read-before-write discipline. However it never states whether omitted fields are preserved (partial vs. full update), what happens on a baseVersion conflict, or whether edits are recoverable via version history.

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?

Three short sentences, front-loaded with the core behavior and the replacement caveat, followed by the prerequisite and the alternative. No redundant restatement of the tool name or schema fields; every sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter mutation tool with no output schema, the description covers the biggest risk (content clobbering) and the required versioning workflow. It is still thin on update semantics — whether unspecified fields are left untouched, conflict handling for baseVersion, and the effect of isArchived/reminder/background changes — which an agent needs to call this safely.

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 56%, and the description meaningfully supplements the highest-risk parameter by explaining that `content` replaces the entire body and must be complete edited markdown. It indirectly explains `baseVersion` by tying it to the get_note read. It adds nothing for the undocumented parameters (id, title, isPinned, isArchived) or for tagIds, reminder, and background, which rely on schema text.

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?

The verb is generic ("Change a note") and it never enumerates what can be changed (title, tags, pin, reminder, background, archive), so the purpose is only partly stated. It does clearly identify the resource and the key operation semantics for `content`, and it distinguishes itself from append_to_note. An agent can tell it is the general mutation tool for an existing note, but must open the schema to learn the full scope.

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 prescribes a prerequisite workflow: read with get_note first, then send full edited markdown. It also names the alternative for the append-only case (append_to_note). It stops short of exclusions for other siblings such as bulk_update_notes, trash_note, or restore_note, so it is clear context without full routing.

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