mcp-context-window

doc_window

Page through large documents by reading chunk ranges. Omit indices to continue from your last position or reset to start, keeping token usage within budget.

Instructions

Read a range of chunks verbatim. This is the sliding window: ask for chunks 0-2, then 3-5, and so on, keeping each read inside your budget. Omit from/to to continue from where the last window left off — the read cursor is stored server-side, so sequential paging works without you tracking position.

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": {
      "doc_id": "<doc_id>"
    },
    "name": "doc_window"
  }
}

Input Schema

Name	Required	Description
`to`	No	Last chunk index (inclusive)
`from`	No	First chunk index (inclusive)
`reset`	No	Move the cursor back to the start
`doc_id`	Yes	Document id returned by doc_ingest
`budget_tokens`	No	Stop before exceeding this many tokens

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Aug 23, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations provided, the description carries the burden of behavioral disclosure. It reveals important stateful behavior: the read cursor is stored server-side, so sequential paging works without the agent tracking position. It also explains budget behavior and the verbatim read nature, which is strong for a read tool.

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?

The description is three sentences with no filler. It front-loads the core purpose, then adds the operational pattern and cursor behavior in a compact, readable way. Every sentence earns its place.

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?

The tool has moderate complexity due to its server-side cursor and budget parameter, and the description covers these well. There is no output schema, but the description does not need to fully specify return format because the read semantics and paging behavior are clear. Minor gaps like error behavior or what happens on a fresh cursor are acceptable.

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. The description adds value beyond the schema by explaining how from/to relate to sliding-window reads, and by clarifying that omitting them continues from the server-stored cursor. This extra context justifies an above-baseline score.

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 starts with a specific verb and resource: 'Read a range of chunks verbatim.' This clearly distinguishes doc_window from siblings like doc_search, doc_summarize, and doc_outline, which do not provide verbatim chunk reads. The sliding-window framing further clarifies its unique role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

The description gives clear practical usage context: it explains the sliding-window pattern, how to stay within budget, and how to continue paging by omitting from/to. It does not explicitly name alternatives or state when not to use this tool, so it stops short of a 5.

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

Deploy Server