quillink-mcp

search_notes

Find matching notes by full-text keywords in titles and body text, optionally filtered by tags; locked notes match only by title to protect hidden content.

Instructions

Full-text search over the caller's active notes' titles and body text, optionally only within notes carrying any of tags (every one with tag_match="all"). Locked notes only match on title (their body is never substring-matched, so a search hit can't leak hidden content).

Input Schema

Name	Required	Default
`q`	Yes
`tags`	No
`limit`	No
`tag_match`	No	any

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 18, 2026

addedInput schema / properties / tag_match

Added value: +{
+  "default": "any",
+  "title": "Tag Match",
+  "type": "string"
+}

addedInput schema / properties / tags

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Tags"
+}

First observedv0.1.0Aug 6, 2026

TDQS

A3.9/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and delivers real value: it scopes search to 'active' notes, discloses that locked notes are only title-matched, and explains that this prevents leaking hidden body content. That security-relevant detail goes well beyond the schema. It does not cover result ordering, pagination, or what happens with empty/whitespace queries.

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 dense sentences, front-loaded with the core operation and then the two edge conditions (tag filtering, locked notes). No filler or restated field names.

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?

The output schema exists, so return values need not be described, and the search scope/edge cases are handled well. However, for a 4-parameter tool with zero schema coverage, the description leaves `limit` and query semantics undefined, so an agent cannot fully reason about call behavior.

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 0%, so the description must compensate. It explains the semantics of `tags` and the `tag_match="all"` value, but `q` and especially `limit` (default 50, no max/pagination meaning) go entirely undocumented in both description and schema. Partial compensation only.

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?

The description names a specific verb (full-text search) and resource (caller's active notes), and pins the searchable fields (titles and body text). This cleanly distinguishes it from siblings like list_notes or get_note, which are enumeration/lookup rather than search.

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?

It states the optional narrowing condition ('only within notes carrying any of tags') which implies when the filter is useful, but it never explicitly says when to choose search_notes over list_notes, get_related_notes, or get_note_backlinks. Usage is left to inference rather than stated.

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