Skip to main content
Glama

search_notes

Read-only

Search Apple Notes by title and body text, returning title matches first and body matches newest first. Add a folder to narrow results in large libraries.

Instructions

Search notes by title and body text. Title matches come first, then body matches, newest first in each group. The body is searched only when the title matches are fewer than 'limit'. Locked notes can match by title only. Large libraries are slow, so give 'folder' when you can.

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": {
      "query": "<query>"
    },
    "name": "search_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost results to return. Default 25, maximum 200.
queryYesText to find in the title or the body. Ignores case.
folderNoFolder name (any case) or id. Default: all folders.
accountNoAccount name, for example iCloud. Ignores case.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish a safe read (readOnlyHint=true, openWorldHint=false), and the description adds genuinely non-obvious behavior: title-before-body ranking, recency ordering within each group, body searched only when title hits are below 'limit', and locked notes matching by title only. The performance warning about large libraries is also useful operational context. Only the shape of returned results 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?

Four compact sentences, front-loaded with purpose, then ranking, then the conditional-body rule, then the performance tip. Every sentence carries information an agent could not get from the schema or annotations.

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 read-only search with no output schema, the description covers ranking, conditional body search, locked-note behavior, and cost. What it omits is what a result actually contains (title only? snippet? ids?), which an agent needs to chain into get_note.

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, but the description adds real meaning beyond the schema: it explains that 'limit' truncates title matches and thereby gates whether the body is searched at all, and frames 'folder' as a performance lever rather than just a filter. 'Account' receives no narrative treatment, which keeps it from a 5.

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?

"Search notes by title and body text" states a specific verb and resource, and immediately scopes what is searched. It is unambiguous against the resource-specific siblings (search_files, search_contacts) 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 Guidelines3/5

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

Offers one real usage cue: pass 'folder' when the library is large, because searches are slow. It gives no explicit when-to-use/when-not guidance and never points to an alternative (e.g. get_note for a known id), so selection guidance is 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.