Skip to main content
Glama

execute

Send text to a shared serial port and read broadcast RX until an expected literal or timeout, returning observed output and additional writes.

Instructions

Send immediately and independently observe SHARED RX until literal expect or timeout.

Other MCP/Telnet clients may write at any time; no command/response queue or isolation. Any client's output can satisfy expect, so a match is not proof your command completed. additional_writes_observed counts subsequent writes from any source during this call. Result is bounded to 64 KiB. No automatic Ctrl+C, retry or input gating after timeout. wait_seconds is deprecated and ignored (v0.1 compatibility); no input lease exists.

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>",
      "text": "<text>",
      "expect": "<expect>"
    },
    "name": "execute"
  }
}

Input Schema

NameRequiredDescriptionDefault
portYes
textYes
expectYes
newlineNo
timeoutNo
encodingNoutf-8
wait_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses the shared, non-isolated RX buffer, that any client's output can satisfy expect, the additional_writes_observed counter, the 64 KiB result bound, and that there is no automatic Ctrl+C, retry, or input gating after timeout. It also flags wait_seconds as deprecated and ignored, preventing a misuse.

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 critical caveat about shared RX and false-positive matches is front-loaded, and nearly every clause carries distinct information. The style is telegraphic in places ('no input lease exists', 'input gating'), which costs a little readability but not much space.

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 network-write tool with no annotations and no output schema, the behavioral picture is unusually complete: concurrency, result size, counter field, and failure behavior after timeout are all covered. The remaining gap is parameter-level detail for port, text, newline, and encoding, which the description never addresses.

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% across seven parameters, so the description must compensate and only partly does: it clarifies expect (literal match), timeout (bounded wait), and wait_seconds (deprecated, ignored). It adds nothing about port, text, newline, or encoding, leaving four of seven parameters undocumented anywhere.

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?

The description states a specific action pair: send text immediately, then independently observe the shared RX stream until a literal expect match or timeout. That is far clearer than the bare name 'execute'. It does not differentiate from siblings such as send or read_output, so an agent must still infer which tool to choose.

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 context is implied through the expect semantics and the shared-RX warning, which tells the agent this is a send-and-wait pattern rather than a filtered read. However, there is no explicit when-to-use versus send, send_bytes, or read_output, and no statement of when this tool should be avoided.

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