Skip to main content
Glama
network-terminal-mcp

network-terminal-mcp

by evgenyzh

read_output

Reads buffered output from a terminal session using a default or independent named cursor, enabling agents to retrieve command results without losing output between reads.

Instructions

Read buffered output from the default or an independent named cursor.

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": {
      "session_id": "<session_id>"
    },
    "name": "read_output"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
offsetNo
reader_idNo
session_idYes

Output Schema

NameRequiredDescriptionDefault
offsetNo
outputYes
truncatedNo
next_offsetNo
oldest_offsetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.5.0
    • addedInput schema / properties / reader_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Reader Id"
      +}
    • removedOutput schema / description
      Removed value: -"A bounded slice of a session's accumulated output."
    • removedOutput schema / properties / next_offset / anyOf
      Removed value: -[
      -  {
      -    "type": "integer"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedOutput schema / properties / next_offset / default
      Removed value: -null
    • addedOutput schema / properties / next_offset / type
      Added value: +"integer"
    • removedOutput schema / properties / oldest_offset / default
      Removed value: -0
    • removedOutput schema / properties / session_id
      Removed value: -{
      -  "title": "Session Id",
      -  "type": "string"
      -}
    • removedOutput schema / properties / truncated / default
      Removed value: -false
    • changedOutput schema / required
      Previous value: -[
      -  "session_id",
      -  "offset",
      -  "output"
      -]New value: +[
      +  "output"
      +]
    • changedOutput schema / title
      Previous value: -"OutputChunk"New value: +"BufferReply"
  2. Changed4 schema fields changedv0.2.1
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / offset / anyOf
      Added value: +[
      +  {
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / offset / default
      Previous value: -0New value: +null
    • removedInput schema / properties / offset / type
      Removed value: -"integer"
  3. First observedv0.1.1

TDQS

C2.4/5.0
Behavior2/5

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

With no annotations, the description carries the full burden. The critical behavioral question for a cursor-read tool — whether reading advances/consumes the cursor or is repeatable, and whether it blocks waiting for new output — is entirely unaddressed, as are error conditions for a bad or closed session_id.

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?

A single front-loaded sentence with no filler, which is good structure. It is arguably too terse for a tool with cursoring semantics, but the wording itself earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

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 not be described. But for a stateful cursor-read tool with four undocumented parameters and no annotations, the definition omits essential context: cursor advancement semantics, pagination via limit/offset, and interoperation with open_session/close_session.

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 0% across four parameters. The phrase 'independent named cursor' loosely signals that reader_id is optional and selects a non-default cursor, but session_id, limit, and offset receive no explanation of meaning, units, or interaction (e.g. does offset apply to the cursor or to the byte stream?).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb (read) and resource (buffered output), and notes the default-vs-named-cursor scope. However, it never clarifies what 'output' belongs to or how this differs from the sibling terminal_read, so an agent cannot confidently choose between the two from the description alone.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance, no prerequisites (e.g. does a session need to be open?), and no reference to alternatives such as terminal_read or session_status. The only implied cue is the choice between default and named cursor.

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