Skip to main content
Glama
JoeGlenn1213

ActionD

by JoeGlenn1213
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Local

actiond_handoff_pack

Read-onlyIdempotent

Generate a handoff package from git log, CI/CD verdicts, task reports so another agent or human resumes with full context. Returns JSON and Markdown with progress, failures, decisions, next action.

Instructions

Generate a handoff package that lets another agent (or human) resume this work with full context, aggregating git log, ActionD CI/CD verdicts, and — when task_id is given — the task report from the connected task management system. Choose actiond_run_report instead when the goal is verifying a completed run rather than transferring the work to a successor. Returns structured JSON plus a ready-to-use Markdown document covering: goal, current state (with evidence level), completed work (recent commits), pending work, known failures, decisions, verification state, and a suggested next action. The markdown field alone is designed to give the receiving agent everything it needs without reading the original session; missing information is marked unknown rather than guessed. Optional path (defaults to the current directory), task_id, project_id, from_agent/to_agent, goal, suggested_next_action, pending_work (comma-separated), and ttl_hours for the validity window (default 24).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalNoOne-sentence task goal
pathNoRepository path (defaults to the current directory)
task_idNoTask ID; when provided, the task report is also queried to fill in goal and decisions
to_agentNoIdentity of the agent receiving the work (e.g., 'claude')
ttl_hoursNoHow long the handoff stays valid, in hours (default 24)
from_agentNoIdentity of the agent handing off the work (e.g., 'codex')
project_idNoProject ID in the task management system (defaults to the repository name)
pending_workNoComma-separated list of pending work items
suggested_next_actionNoNext step the receiving agent should take

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv0.1.1
    • changedInput schema / properties / from_agent / description
      Previous value: -"交接发起方（如 dsh:codex）"New value: +"Identity of the agent handing off the work (e.g., 'codex')"
    • changedInput schema / properties / goal / description
      Previous value: -"任务目标一句话"New value: +"One-sentence task goal"
    • changedInput schema / properties / path / description
      Previous value: -"仓库路径（默认当前目录）"New value: +"Repository path (defaults to the current directory)"
    • changedInput schema / properties / pending_work / description
      Previous value: -"待办清单（逗号分隔）"New value: +"Comma-separated list of pending work items"
    • addedInput schema / properties / project_id
      Added value: +{
+  "description": "Project ID in the task management system (defaults to the repository name)",
+  "type": "string"
+}
    • changedInput schema / properties / suggested_next_action / description
      Previous value: -"建议接手方执行的下一步"New value: +"Next step the receiving agent should take"
    • changedInput schema / properties / task_id / description
      Previous value: -"任务 id；提供后同时查询 RMS task report 补全 goal/decisions"New value: +"Task ID; when provided, the task report is also queried to fill in goal and decisions"
    • changedInput schema / properties / to_agent / description
      Previous value: -"接手方（如 dsh:claude-window）"New value: +"Identity of the agent receiving the work (e.g., 'claude')"
    • changedInput schema / properties / ttl_hours / description
      Previous value: -"交接有效期小时（默认 24）"New value: +"How long the handoff stays valid, in hours (default 24)"
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint, so description adds context about aggregating git log, CI/CD verdicts, and task report, plus return format (structured JSON and Markdown) and handling of missing info as unknown. No contradiction with annotations.

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?

The description is dense but front-loaded with purpose and differentiation. It uses several sentences but each adds value, though it could be slightly trimmed for brevity without losing key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 9 optional parameters and no output schema, the description fully explains what it returns (structured JSON plus Markdown with specific sections) and behavior (missing info marked unknown). It also covers defaults and alternative selection, making it complete for correct invocation.

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 covers all 9 parameters at 100%, but description adds semantic context: task_id triggers task report query to fill goal and decisions, pending_work is comma-separated, ttl_hours defines validity window. This adds value beyond the schema, though not dramatically.

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 ('generate a handoff package') and explicitly names the sibling actiond_run_report to differentiate when to use it. The purpose is unambiguous and distinguishes the tool from its siblings 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Choose actiond_run_report instead when the goal is verifying a completed run rather than transferring the work to a successor,' providing clear when-not-to-use guidance. Also explains when task_id is given, it queries the task report, giving conditional usage context.

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