Skip to main content
Glama

call_cli

Run allowlisted CLI commands for supported catalog peers such as GitHub, Railway, Vercel, Supabase, Stripe, and Slack; for Claude, Codex, or ChatGPT, open the extension instead.

Instructions

Run an allowlisted CLI for a catalog platform peer (gh, railway, vercel, supabase, stripe, slack). Rejected for claude/codex/chatgpt — open the extension instead.

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": {
      "peer": "<peer>",
      "argv": "<argv>"
    },
    "name": "call_cli"
  }
}

Input Schema

NameRequiredDescriptionDefault
argvYes
peerYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

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 behavioral burden. It does disclose a real constraint an agent could not otherwise know: execution is gated by an allowlist and certain peers are actively rejected. It omits whether the CLI runs with write side effects, what permissions or credentials are used, and any timeout or sandbox behavior.

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?

Two dense sentences with the action and scope front-loaded, and no filler. The trailing exclusion clause is compact and earns its place, though 'open the extension' is terse to the point of being cryptic.

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 two-parameter execution tool with no annotations and no output schema, the definition covers the input domain reasonably but says nothing about what comes back (stdout, exit code, error shape) or how failures surface. An agent can construct a call but cannot predict or interpret the result.

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 compensate. It substantially clarifies `peer` by enumerating the accepted catalog platforms, which the bare string schema does not convey. It says nothing about `argv` beyond the schema's array-of-strings/minItems=1, leaving the agent to guess whether it is the full command line or arguments appended to the peer's binary.

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?

Specific verb plus resource: 'Run an allowlisted CLI' scoped to 'a catalog platform peer', with concrete example peers (gh, railway, vercel, supabase, stripe, slack) that make the domain unambiguous. It does not name any sibling tool (call_api, route, slack_api), so differentiation from those must be inferred, but the allowlist framing does separate it from a generic API caller.

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?

It states a when-not condition ('Rejected for claude/codex/chatgpt') and points to a fallback, which is more than most definitions offer. However, the fallback ('open the extension instead') is not a tool name and does not map to any sibling, so the agent cannot actually route on it, and there is no guidance on choosing this over call_api.

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