Skip to main content
Glama

execute_verified_command

Executes approved dev/test commands in a sandboxed, isolated workspace and records independently verified execution evidence for tamper-evident reporting.

Instructions

Executes an approved dev/test command in a sandboxed, isolated environment within the workspace and records independently verified execution evidence (provenance: server_executed).

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": {
      "bundleId": "<bundleId>",
      "command": "<command>"
    },
    "name": "execute_verified_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoOptional working directory relative to workspace root.
envNoOptional custom environment variables (sensitive tokens will be rejected).
argsNoArguments array passed directly to the command.
commandYesThe executable command to run (e.g. "npm", "git", "node", "vitest").
bundleIdYesThe unique identifier of the evidence bundle.
timeoutMsNoExecution timeout in milliseconds (default 30000).
workspaceNameNoOptional registered workspace/package name (defaults to primary root).
workspacePathNoOptional workspace path hint.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.4.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden and does deliver that execution happens in a sandboxed, isolated environment and that evidence is recorded server-side. It omits the meaningful risks: whether execution is blocking, what happens on timeout or non-zero exit, whether a non-approved command is rejected, and that sensitive env tokens are refused (that detail lives only in the schema).

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 dense sentence that front-loads the action and appends the evidence side effect, with no filler. The parenthetical provenance note is compact and functional, though the sentence is somewhat overloaded with the isolation, approval, and evidence concepts in one breath.

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 an eight-parameter execution tool with a nested env object and no output schema, the description covers the essential posture (sandboxed, isolated, evidence-recording) but leaves the approval mechanism, failure behavior, and the shape of the recorded evidence entirely undefined. An agent knows roughly what it does but not what to expect back.

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 100% for all eight parameters including the nested env object, so the baseline is 3. The description adds no argument-level detail beyond reinforcing that the command must be approved; it does not clarify bundleId's role in the evidence pipeline or how cwd/workspaceName interact.

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 gives a specific verb and resource — executes an approved dev/test command — and adds two differentiating traits: sandboxed isolation and evidence recording with provenance server_executed. It separates the tool from read-only evidence capture siblings, though it never names record_command_result, which is the nearest overlap.

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?

The qualifier 'approved dev/test command' implies a usage boundary, but the description never explains what makes a command approved, how that approval is established, or when an agent should use this rather than recording a result through record_command_result. The guidance is implied rather than stated.

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