Skip to main content
Glama

read_output

Read serial RX data without consuming other sessions' output, then reuse the returned cursor for incremental reads. Supports wait time, byte limits, and encodings.

Instructions

Read RX without consuming other sessions' data. Reuse returned cursor for increments.

No cursor replays retained buffer. base64 is lossless; text can split UTF-8 chunks. Old cursors are rejected after close/reopen. bytes_lost reports ring overflow.

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

Input Schema

NameRequiredDescriptionDefault
portYes
cursorNo
encodingNoutf-8
max_bytesNo
wait_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations provided, the description carries the full load and does so well: non-consuming multi-session reads, cursor lifecycle (old cursors rejected after close/reopen), ring-buffer overflow surfaced via bytes_lost, and the lossy-chunking caveat for text encoding. The notable omission is blocking behavior tied to wait_seconds, which an agent needs to know to avoid hanging.

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?

The purpose leads, followed by cursor and encoding behavior in four tight lines with no filler. A few phrasings are telegraphic to the point of ambiguity, e.g. "No cursor replays retained buffer" takes a second read to parse.

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

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter, no-output-schema, no-annotation tool the description covers the tricky read/cursor semantics well but leaves max_bytes and wait_seconds undefined, so an agent cannot predict buffer sizing or blocking behavior from the definition alone.

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 coverage is 0%, so the description must compensate for all five parameters. It meaningfully documents cursor (reuse, no-cursor replay, rejection after reopen) and encoding (base64 lossless vs text splitting UTF-8), but port, max_bytes, and especially wait_seconds get no explanation at all.

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?

"Read RX without consuming other sessions' data" states a specific verb and resource plus the key non-destructive read semantics, which separates it from sibling write paths like send or execute. It never names a sibling tool explicitly, so differentiation is implied rather than stated.

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?

"Reuse returned cursor for increments" tells the agent the intended calling pattern for repeated reads, and "No cursor replays retained buffer" clarifies the fresh-read case. It stops short of explicit when-not guidance or pointing to alternatives such as port_status for other kinds of inspection.

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