Skip to main content
Glama

request_access

Ask a person to approve SSH access to specific hosts and scopes, with your reason, before you connect. Waits for their answer, which may grant less than you asked.

Instructions

Ask the person for access to hosts. They see your name, the hosts, the scopes and your reason, and may allow less than you asked. Waits up to 100 seconds for the answer; if it is still pending, ask the person to approve it: their answer takes effect by itself, and wait_for_access waits for it.

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": {
      "hosts": "<hosts>",
      "scopes": "<scopes>",
      "reason": "<reason>"
    },
    "name": "request_access"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostsYesHosts by name, as list_hosts shows them (`team/name` for a team's host).
reasonYesWhat you are going to do and why, in a sentence the person reads before approving.
scopesYesWhat you need to do there. Prefer `connect` over `exec` unless you will run many commands.
durationNoFor how long; the person may change it. Default: 2h.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full behavioral burden, and it does so well: it discloses what the person sees, that the grant may be narrower than requested, the ~100-second wait window, and that an answer takes effect automatically. It does not say what is returned or what happens on denial, which is the main remaining gap.

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?

Three sentences, front-loaded with the action and the human-facing consequence, then the timeout, then the handoff. Every sentence earns its place; the final sentence is slightly packed but carries actionable flow information.

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 an approval-flow tool with no annotations and no output schema, it covers the interaction model, timeout, partial grants, and the follow-up tool needed to complete the flow. It stops short of describing the result or denial behavior, which is the one thing an agent would still have to discover at runtime.

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%, so the schema already documents hosts, scopes, reason and duration, including the per-scope semantics. The description adds only one parameter-level fact — that the person may allow less than asked, i.e. scopes and duration can come back reduced — which is useful but modest, so the baseline 3 holds.

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?

States a specific verb and resource ('Ask the person for access to hosts') and immediately names the sibling it hands off to ('wait_for_access'). An agent can tell this apart from wait_for_access without opening either 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?

Clear usage context: it describes the escalation path — call this, and if the request is still pending after ~100 seconds, prompt the person and then use wait_for_access. It does not state explicit exclusions (e.g. don't request scopes you already hold), but the when-to-use and alternative routing are unambiguous.

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