RLM MCP Server

Read Context Portion

rlm_read_context

Read-onlyIdempotent

Read specific sections of a context by character or line ranges. Examine targeted parts without loading the full context, enabling efficient processing of long inputs.

Instructions

Read a specific portion of the context.

Modes:

chars: Read by character offsets (start, end)
lines: Read by line numbers (start, end)

Use this to examine specific sections without loading the entire context.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "rlm_read_context"
  }
}

Input Schema

Name	Required	Description	Default
`end`	No	End position (exclusive)
`mode`	No	Read by character offsets or line numbers	chars
`start`	No	Start position (character offset or line number)
`context_id`	No	Context identifier	main
`session_id`	No	Session ID

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.0.0Aug 2, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds context about modes (chars/lines) and the purpose of reading portions, but it does not describe return format, behavior for out-of-range positions, or how session/context IDs interrelate. This is similar to the TDQS get_calls baseline where annotations cover safety and description adds some context but not full behavioral disclosure.

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 very concise: a single opening sentence, a structured mode list, and a one-line usage guideline. Every sentence earns its place, and the key information is front-loaded.

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?

For a simple read operation with full schema coverage and strong annotations, the description is mostly complete. It explains what it does and the modes. However, since there is no output schema, the description could clarify the return format (e.g., it returns the text portion). The behavior for invalid ranges or when the portion is unavailable is also not described, so it loses one point.

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 description coverage is 100%, with each parameter having a clear description (e.g., 'Start position (character offset or line number)', 'End position (exclusive)'). The description adds little beyond restating modes and the general purpose, so the baseline score of 3 is appropriate.

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 clearly states the tool reads a specific portion of the context, with a specific verb and resource. It distinguishes itself from siblings like rlm_load_context by emphasizing 'specific portion' and 'without loading the entire context', and from get_context_info/get_chunks by focusing on direct reading by offsets or line numbers.

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 provides clear guidance: 'Use this to examine specific sections without loading the entire context.' This gives a strong usage context and implicitly contrasts with loading full context. It doesn't explicitly name alternatives or exclusions, but the guidance is clear about when to use this tool.

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

Deploy Server