Skip to main content
Glama

agent_resume

Resume a closed Claude or Codex worker from its recorded session, restoring its full prior context and identity. Address it by name or agent_id, then send follow-up instructions via agent_send.

Instructions

Resume a CLOSED claude or codex worker from its recorded session id (claude --resume / codex resume): a fresh pane, the same actor_id, and the worker's full prior context. Addressed by name or agent_id among closed agents (agent_list(include_closed: true)). Send it its next instruction with agent_send once resumed - this tool does not.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoThe worker's name, e.g. "impl" or "DEVX-123". Prefer passing this rather than agent_id, but pass only one: if both arrive, agent_id wins and this is ignored. A partial name works when it matches exactly one running worker, so "123" finds DEVX-123.
agent_idNoNumeric agent id. Use name instead unless you have the id to hand.
project_idNoDifferent project override. Use ONLY when the user explicitly asks for another project by name; otherwise stay in the current scope, even when results are empty.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
actor_idYes
agent_idYes
tmux_targetYes
branch_driftNo
was_parked_atNo
landed_in_projectNo
resumed_session_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it delivers: it discloses prerequisites (agent must be closed), the exact effects (fresh pane, same actor_id, full context restored), and a key limitation (does not send instructions). With zero annotation coverage, this is well above average, though it omits the failure behavior for calls on a running worker.

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?

Front-loaded with the core purpose, and every sentence earns its place: effects, addressing rule, and the agent_send follow-up. The claude/codex parenthetical adds cross-tool clarity without bloat. It is dense but compact—no filler, though it slightly crams multiple clauses into the opening sentence.

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?

Comprehensive for a moderate tool: purpose, addressing, post-conditions, and follow-up action are all covered, and the presence of an output schema means return values need no duplication. The only gap is the absence of any explicit error-state behavior (e.g., 'errors if the agent is already running'), but the CLOSED qualifier conveys the intent.

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 detailed per-parameter guidance (prefer name, agent_id wins on conflict, project_id only on explicit request), so the baseline of 3 applies. The description adds only marginal context—'addressed by name or agent_id among closed agents'—which confirms rather than extends the schema's already thorough semantics.

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?

Specific verb (Resume) + resource (a CLOSED claude or codex worker), with concrete effects spelled out: fresh pane, same actor_id, full prior context. The claude --resume / codex resume analogy reinforces the concept. Clearly distinguishable from siblings like agent_spawn (creates a new worker) and agent_park/agent_close (state changes the other direction).

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?

States the operative constraint (only CLOSED agents), how to find them (agent_list(include_closed: true)), and explicitly routes the follow-up to agent_send, clarifying that this tool does NOT deliver the next instruction. It implies the 'don't use for running agents' exclusion via the CLOSED qualifier but never states it negatively; still, the routing and alternative tool naming are strong.

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