devonthink3-mcp

Overview Schema Source Related Servers Discussions Admin

dt3_related

Read-onlyIdempotent

Find similar documents, classification suggestions, duplicate files, and incoming/outgoing references for a DEVONthink record UUID to support organization and linking decisions.

Instructions

Find native similar documents, classification suggestions, duplicate files, or incoming/outgoing item references. Results are permission-filtered. Suggestions are advisory; duplicate detection follows DEVONthink, not a fresh disk hash.

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": {
      "uuid": "<uuid>",
      "kind": "<kind>"
    },
    "name": "dt3_related"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes
`uuid`	Yes	Record UUID or x-devonthink-item:// link. Link page/search parameters are ignored.
`limit`	No
`offset`	No

Output Schema

Name	Required	Description	Default
`kind`	No
`records`	Yes
`advisory`	No
`snapshot`	Yes
`next_offset`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.3.0Nov 11, 2026
- changedInput schema / properties / limit / maximum
```
Previous value: -100New value: +200
```
First observedv0.2.0Sep 8, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: results are permission-filtered, classification suggestions are advisory only, and duplicate detection reflects DEVONthink's own index rather than a fresh disk hash — the last point materially affects how an agent should interpret and trust the output.

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 purpose, followed by the two most consequential caveats (permission filtering, duplicate semantics). No filler and no restatement of the tool name.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers the crucial interpretive caveats for a read-only lookup tool. The remaining gap is pagination semantics for limit/offset, which is minor given the schema's explicit bounds and defaults.

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 only 25% — only 'uuid' is documented in the schema (including the item-link format and ignored link parameters), while 'limit' and 'offset' have no textual explanation anywhere. The description partially compensates by naming the five result modes that correspond to the 'kind' enum, but pagination behavior for limit/offset is left entirely unexplained.

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 description opens with a specific verb ('Find') and enumerates exactly what is returned: similar documents, classification suggestions, duplicates, and incoming/outgoing references, which maps cleanly onto the five 'kind' enum values. It does not explicitly contrast itself with dt3_search or dt3_get_record, but the mode list is distinctive enough that an agent can tell it apart from generic retrieval tools.

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?

Usage is implied by the enumerated modes: an agent can infer that 'similar' is for finding related items and 'duplicates' for duplicate hunting. However, there is no explicit statement of when to prefer this over dt3_search, nor any exclusion or prerequisite guidance, so the agent must infer routing from the sibling names alone.

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

Deploy Server