devonthink3-mcp

Overview Schema Source Related Servers Discussions Admin

dt3_read_text

Read-onlyIdempotent

Read a bounded chunk of DEVONthink indexed plain text with citation and extraction status. Use it to retrieve specific passages from a DEVONthink record without OCR or transcription.

Instructions

Read a bounded chunk of DEVONthink indexed plain text with citation and extraction status. No OCR, transcription, or spreadsheet recalculation is performed.

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>"
    },
    "name": "dt3_read_text"
  }
}

Input Schema

Name	Required	Description
`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
`text`	Yes
`offset`	Yes
`record`	Yes
`source`	Yes
`untrusted`	Yes
`next_offset`	Yes
`text_status`	Yes
`total_characters`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.3.0Nov 11, 2026
- changedInput schema / properties / limit / maximum
```
Previous value: -16000New value: +64000
```
First observedv0.2.0Sep 8, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed world), so the bar is lower, and the description still adds real information: output carries citation and extraction status, and the tool performs no OCR/transcription/recalculation. That negative scope is the key behavioral fact an agent needs before trusting the returned text as complete. It stops short of stating what happens on a UUID miss or how truncation is signaled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no padding, with the core action front-loaded before the exclusion clause. The phrase "with citation and extraction status" is compressed to the point of being slightly ambiguous, but every sentence earns its place.

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?

An output schema exists, so return-value explanation is not required, and the annotations cover the safety profile. However, for a chunked-read tool the description omits practical essentials: the units and semantics of limit/offset, and how the agent detects that it has only a partial chunk. Adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (only uuid is documented), so the description must compensate, and it does not. "Bounded chunk" gestures at limit/offset but never says what unit they use (characters vs. bytes), nor what the defaults or maximums mean in practice, leaving two of three parameters as opaque integers.

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?

"Read a bounded chunk of DEVONthink indexed plain text" gives a specific verb, a specific resource, and a clear scope (chunked access rather than whole-document). It implicitly separates itself from the plural dt3_read_texts, but never names that sibling or states the single-vs-batch distinction explicitly.

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?

There is no explicit when-to-use statement and no named alternative for batch reads, which is the most likely confusion given dt3_read_texts exists. The negation clause (no OCR, transcription, or spreadsheet recalculation) does function as an implicit boundary, telling the agent this tool will not yield text from scanned images or spreadsheets, so usage 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.

Deploy Server