read_documentReads document text, including scanned files via OCR, and returns the first page by default; use offset to continue through longer documents.
Text of a document, first page by default (scans via local OCR). next_offset continues.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| offset | No | ||
| max_chars | No |
Changes observed during successful MCP inspections.
v0.1.1Input schema / properties / max_chars / defaultPrevious value: -20000New value: +2500Input schema / properties / offsetAdded value: +{
+ "default": 0,
+ "title": "Offset",
+ "type": "integer"
+}Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "additionalProperties": true,
- "title": "Result",
- "type": "object"
- }
- },
- "required": [
- "result"
- ],
- "title": "read_documentOutput",
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds real value by disclosing the default page scope, local OCR for scans, and the next_offset continuation mechanism. It omits what happens on a missing/unreadable path and gives no sense of output size beyond the max_chars default.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short clauses, front-loaded with the result and default scope, with zero filler. The telegraphic style costs some readability and makes the pagination note easy to misparse, but nothing is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read tool with annotations covering safety and no output schema, the description covers the default scope and continuation. It is not complete enough about truncation behavior and max_chars, which an agent needs to decide whether one call suffices.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must carry parameter meaning and it only partially does: 'next_offset continues' effectively explains the offset parameter's role. max_chars is never mentioned at all, and path conveys nothing beyond its name, leaving a real gap on a 3-parameter tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
It states a specific resource and result — 'Text of a document' — and adds a scope qualifier ('first page by default') plus OCR behavior for scans, so an agent knows what it gets back. It is written as a fragmented noun phrase rather than a verb+resource sentence, and it never distinguishes itself from siblings like search or list_folder.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'first page by default' and 'next_offset continues' imply the pagination workflow, which is genuine usage guidance for continued reading. However, there is no explicit when-to-use-vs-alternatives guidance against siblings such as search or catalog_describe, leaving the agent to infer selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.