Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_workspace_read

Read-onlyIdempotent

Reads a UTF-8 text file from an engagement workspace, using offset and bounded byte ranges to inspect large files in controlled chunks.

Instructions

Read a UTF-8 text file from the OpenCyber engagement workspace. Returns at most max_bytes (default 1 MiB); a bounded read reports total_bytes, next_offset, and a continuation. Set max_bytes=0 for the whole file.

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": {
      "engagement_id": "<engagement_id>",
      "path": "<path>"
    },
    "name": "oc_workspace_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
offsetNo
max_bytesNo
engagement_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral detail: a 1 MiB default cap, the escape hatch max_bytes=0 for full-file reads, and the presence of a continuation token for paging. It stops short of describing failure behavior for missing or non-UTF-8 files.

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 tight sentences, each earning its place: the core action first, then the size bound and return fields, then the override. 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 values need no prose explanation, and the description correctly focuses on the pagination contract an agent must know to read a large file. The remaining gap is path/engagement_id semantics and error behavior, minor for a read-only tool.

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 0%, so the description must compensate, and it does so well for max_bytes (default size, sentinel value of 0) and indirectly for offset via next_offset/continuation. However, path semantics (absolute vs engagement-relative) and engagement_id are completely unexplained, leaving half the parameters undocumented in both schema and description.

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?

States a specific verb and resource: 'Read a UTF-8 text file from the OpenCyber engagement workspace.' The 'UTF-8 text file' qualifier and workspace scoping implicitly distinguish it from binary or device reads, but it never names a sibling such as oc_serial_read or oc_workspace_list to make the boundary explicit.

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 only implied by the resource location ('workspace') and the UTF-8 text constraint. There is no explicit statement of when to prefer this over oc_workspace_list or oc_serial_read, and no guidance on error cases such as a missing path or non-text file.

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

Deploy Server

Other Tools