Skip to main content
Glama
Sign In
spillway-mcp

spillway-mcp

by Secret-art-stack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

codex_followup

Read-only

Continue an explicit completed Codex session in the same workspace and model for bounded read-only research. Requires a session ID and never resumes the latest ambient session.

Instructions

Continue an explicit completed Spillway Codex session in the same workspace/home and model. Always read-only; never resumes the latest ambient session.

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": {
      "prompt": "<prompt>",
      "session_id": "<session_id>"
    },
    "name": "codex_followup"
  }
}

Input Schema

NameRequiredDescriptionDefault
cwdNoWorkspace directory (defaults to the server workspace).
modelNoExplicit Codex model slug; defaults to SPILLWAY_CODEX_MODEL. Availability is account-dependent.
effortNohigh
promptYesBounded read-only research task. No file edits or delegation.
wait_msNoWait budget; returns a job handle if still running.
session_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.4.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so 'Always read-only' is largely a restatement. The genuinely additive behavior is the constraint that it never resumes the latest ambient session and stays in the same workspace/home/model, but return behavior (job handle vs. result) and failure modes for a non-completed session_id are left to 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.

Conciseness5/5

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

Two short sentences, front-loaded with the action and scope, followed by the key exclusion. No filler or repeated annotation content beyond a brief reinforcement.

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 6-parameter continuation tool with no output schema, the description covers scope and read-only nature but omits what happens when session_id is unknown or not completed, and how wait_ms versus a returned job handle (per schema) should be handled by the caller.

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 coverage is 67%, with cwd, model, prompt, and wait_ms documented inline; session_id and effort are undocumented in both places. The description adds the meaningful nuance that workspace/home and model carry over from the original session, but does not explain session_id semantics or the effort enum.

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?

States a specific verb ('Continue') and resource ('an explicit completed Spillway Codex session'), and pins the scope with 'in the same workspace/home and model'. It implicitly separates itself from ambient/latest-session resumption, though it never names a sibling tool like codex_research or codex_status.

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 phrase 'explicit completed ... session' and 'never resumes the latest ambient session' effectively tells the agent the precondition (an existing, finished, ID-addressed session) and rules out the wrong usage. What's missing is an explicit pointer to the alternative when no completed session exists.

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