Skip to main content
Glama

digest_command

Runs your build, tests, linter, or DRC command and returns a verdict instead of raw output: exit code, checked error quotes, last lines, and the full log path.

Instructions

Run a command of yours (build, tests, linter, DRC) and get the verdict instead of the output.

Returns the exit code, the answer of the executor to question (default: did it succeed, and what are the errors) with checked quotes, the last lines of the output, and the path of the full output in case you need to read a part yourself. The command runs as you wrote it, with your rights: the limits apply only to commands the executor chooses.

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": {
      "command": "<command>",
      "cwd": "<cwd>"
    },
    "name": "digest_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdYes
commandYes
timeoutNo
questionNo
max_wordsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.1

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the return payload (exit code, executor answer with checked quotes, tail lines, path to full output), notes the command executes as written with the caller's rights, and clarifies that limits apply only to executor-chosen commands. Gaps remain on timeout behavior, failure-timeout semantics, and any sandboxing or side effects of running an arbitrary command.

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 single-sentence hook is front-loaded and the second sentence efficiently enumerates the response components. The closing sentence about running "with your rights" is somewhat compressed and takes a moment to parse, but nothing is wasted.

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?

The output schema exists, so return shape need not be spelled out, and the description focuses on the answer/question contract where it adds value. But for a tool that executes arbitrary commands with no annotations, missing timeout/limit behavior and unexplained `cwd`/`max_words` leave real gaps an agent would want covered.

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 explain the 5 parameters, and it explains two: `command` (runs verbatim with your rights) and `question` (defaults to asking whether it succeeded and what the errors are, answered with checked quotes). `cwd`, `timeout`, and `max_words` are never mentioned, leaving their semantics to inference from names and defaults.

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?

"Run a command of yours (build, tests, linter, DRC) and get the verdict instead of the output" states a specific verb (run a command) plus the distinctive contract (digest/verdict rather than raw stdout), and the "of yours" / "commands the executor chooses" phrasing separates it from executor-run siblings such as executor_probe. An agent can tell what it is and what it is not without opening the schema.

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 opening clause sets the use case (you have a command and want the verdict, not the log), and "the path of the full output in case you need to read a part yourself" gives the fallback route when the digest is insufficient. It does not name a sibling alternative explicitly and gives no when-not condition, so it stops short of a 5.

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