Skip to main content
Glama
Sign In
llm-cli-gateway

llm-cli-gateway

by verivus-oss
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

session_create

Create a gateway session record for a provider CLI and return a plain UUID for session bookkeeping. Use this when starting a new session through the gateway.

Instructions

Create a gateway session record for a provider. NOTE: this is gateway bookkeeping (a plain UUID), not a provider-native session; Codex resume needs a real Codex UUID.

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": {
      "cli": "<cli>"
    },
    "name": "session_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
cliYesProvider type (claude|codex|gemini|grok|mistral|devin|cursor|grok-api)
descriptionNoSession description
setAsActiveNoSet as active session

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.2.0
  2. Removedv3.0.0
  3. First observedv2.16.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only state readOnlyHint=false, so the description carries the burden of explaining the mutation. It adds meaningful context: the created record is a plain UUID, not a provider-native session, and does not satisfy Codex resume. This goes beyond the schema, though it does not disclose return values or side effects like setAsActive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler: the first states the core operation, the second delivers the critical caveat. Every sentence earns its place and the key limitation is front-loaded near the main purpose.

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 simple create operation with full schema coverage and basic annotations, the description is mostly complete and includes the essential caveat about provider-native sessions. It does not explicitly state the return value or that setAsActive defaults to true, which would be useful given there is no output schema, but these are minor gaps.

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%, with each parameter (cli, description, setAsActive) already documented in the input schema. The description adds no additional parameter-level meaning, so the baseline score of 3 applies.

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?

Description specifies a concrete action ('Create') on a specific resource ('gateway session record') and clearly distinguishes it from provider-native sessions via the plain-UUID note. This differentiates it from sibling tools like codex_fork_session and codex_request without needing to inspect schemas.

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 warning that Codex resume needs a real Codex UUID provides an explicit when-not-to-use condition, and the 'gateway bookkeeping' phrasing clarifies the tool's narrow role. However, it does not name an alternative tool to use instead, leaving the agent to infer from sibling names.

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

Deploy Server

Other Tools