Skip to main content
Glama
anchor-notes-mcp

anchor-notes-mcp

by NatanaelJose

search_notes

Read-only

Find and list Anchor notes by keyword, tag, or scope; results include Markdown content, and unmatched active searches fall back to recent notes.

Instructions

List (no search) or search the user's Anchor notes. Results include each note's markdown content (first 1500 chars). If a search of active notes matches nothing, recent notes are returned instead.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoDefault 20
scopeNoDefault active
tagIdNoOnly notes with this tag (ids from list_tags)
searchNoSubstring to find in titles and content; one short word works best

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare this a safe, closed read, so the description's added value is the non-obvious behavior: results are truncated to the first 1500 chars of markdown, and a search of active notes that matches nothing silently falls back to recent notes. That fallback is exactly the kind of surprise an agent needs warning about; only the return shape beyond content is left unstated.

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 short sentences with zero filler; the primary action comes first and the two behavioral caveats (truncation, empty-match fallback) follow immediately.

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 no output schema, the description carries the burden of describing returns and does so partially by naming markdown content and the 1500-char cap, plus the fallback result set. Missing is anything about ordering, pagination beyond limit, or what metadata accompanies each note, which is a moderate but not severe gap.

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%, so limit, scope, tagId and search are all documented in the schema. The description only adds the mode-switching meaning of the search parameter; it adds no format or constraint detail beyond what the schema already provides, so baseline 3 applies.

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?

States a specific verb+resource ('List ... or search the user's Anchor notes') and makes the two operating modes explicit. It does not distinguish itself from content-reading siblings like get_note, but the core action is unambiguous.

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

Usage Guidelines3/5

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

The description implies the selection rule via '(no `search`)': omit the parameter to list, supply it to search. It offers no guidance against alternatives such as get_note for a single note's full content, and no prerequisites or exclusions are stated.

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