Skip to main content
Glama

Continue Claude Code session

claude_continue

Resume a Claude Code thread by passing the same workspace directory, so follow-up prompts retain repo context after restarts for hosts outside Claude Code.

Instructions

Continue the Claude Code session, for hosts other than Claude Code: resumes the thread rooted at this workspace, so pass the same workspace= as the ask (without it the sub-agent sees no repo). After a restart it resumes the newest Claude Code session there. sandbox applies per turn. Autonomous agent: trusted prompts only.

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>"
    },
    "name": "claude_continue"
  }
}

Input Schema

NameRequiredDescriptionDefault
watchNoIf true, open the live "watch" view. Default false.
promptYesFollow-up message.
sandboxNoPermission policy for THIS turn (default "read-only"). Same values and caveats as claude_ask.read-only
timeout_sNoMax seconds to wait for claude to complete. Default 180.
workspaceNoWorking directory of the prior session. Defaults to the server cwd.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.37.1

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already flag this as non-read-only, open-world, non-idempotent, so the mutation profile is covered. The description adds useful behavior beyond that: it resumes the newest session after a restart, sandbox applies per turn rather than globally, and a missing workspace silently degrades the sub-agent's context. It does not discuss failure modes such as timeout expiry or what a resume returns.

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?

Purpose and the critical workspace requirement are front-loaded, and the sentences are dense with real content. The telegraphic final fragment ("Autonomous agent: trusted prompts only.") is cryptic and costs a bit of clarity.

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?

An output schema exists, so return values need no explanation, and the session-continuity and workspace pitfalls that an agent would otherwise trip over are covered. Minor gaps remain around restart edge cases and timeout behavior, but nothing essential to calling it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely adds meaning: workspace must match the prior session's directory and omitting it breaks repo visibility, and sandbox is scoped per turn. It says nothing extra about prompt, watch, or timeout_s beyond the schema.

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+resource ("Continue the Claude Code session") and describes the mechanics of resuming the thread rooted at the workspace, which separates it from the *_ask siblings by naming the "ask" as the prior call. The qualifier "for hosts other than Claude Code" is somewhat confusing phrasing, and it never explicitly says to use claude_ask instead when starting a new session.

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?

Gives concrete operational guidance: pass the same workspace=<project dir> as the original ask, with the consequence stated ("without it the sub-agent sees no repo"), plus a constraint on prompt trust level. It stops short of an explicit when-to-use-this-vs-claude_ask rule, leaving the continue-vs-ask decision to be inferred from the names.

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