Skip to main content
Glama

rework_task

rework_task
Destructive

Rework a failed or needs-attention task by requeueing it for continued execution with the same agent, project, and round. Add feedback to guide the retry, such as a summary of the previous acceptance failure.

Instructions

手动返修:把终态任务(failed/needs_attention)重新入队续跑,同一 agent/项目与轮次记账。feedback 为追加指示(建议带上一次验收失败摘要)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskIdYes
feedbackNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okNo
modeNo
modelNo
roundNo
checksNo
resultNo
statusNo
taskIdNo
agentIdNo
logFileNo
messageNo
diffstatNo
errorTypeNo
finishedAtNo
abortSourceNo
projectPathNo
reportFilesNo
reportRoundNo
cancelReasonNo
changedFilesNo
keptInstanceNo
lastRunSignalNo
modelProviderNo
needsUserKindNo
agentEndReasonNo
permissionModeNo
zcodeSessionIdNo
pendingQuestionNo
progressSummaryNo
boundProjectPathNo
cancelRequestedAtNo
verificationSourceNo
latestVerificationVerdictNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.0
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "abortSource": {
      +      "type": "string"
      +    },
      +    "agentEndReason": {
      +      "type": "string"
      +    },
      +    "agentId": {
      +      "type": "string"
      +    },
      +    "boundProjectPath": {
      +      "type": "string"
      +    },
      +    "cancelReason": {
      +      "type": "string"
      +    },
      +    "cancelRequestedAt": {
      +      "type": "string"
      +    },
      +    "changedFiles": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "checks": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "durationMs": {
      +            "type": "number"
      +          },
      +          "name": {
      +            "type": "string"
      +          },
      +          "passed": {
      +            "type": "boolean"
      +          }
      +        },
      +        "required": [
      +          "name",
      +          "passed",
      +          "durationMs"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "diffstat": {
      +      "type": "string"
      +    },
      +    "errorType": {
      +      "type": "string"
      +    },
      +    "finishedAt": {
      +      "type": "string"
      +    },
      +    "keptInstance": {
      +      "type": "boolean"
      +    },
      +    "lastRunSignal": {
      +      "type": "string"
      +    },
      +    "latestVerificationVerdict": {
      +      "type": "string"
      +    },
      +    "logFile": {
      +      "type": "string"
      +    },
      +    "message": {
      +      "type": "string"
      +    },
      +    "mode": {
      +      "type": "string"
      +    },
      +    "model": {
      +      "type": "string"
      +    },
      +    "modelProvider": {
      +      "type": "string"
      +    },
      +    "needsUserKind": {
      +      "type": "string"
      +    },
      +    "ok": {
      +      "type": "boolean"
      +    },
      +    "pendingQuestion": {
      +      "type": "string"
      +    },
      +    "permissionMode": {
      +      "type": "string"
      +    },
      +    "progressSummary": {
      +      "type": "string"
      +    },
      +    "projectPath": {
      +      "type": "string"
      +    },
      +    "reportFiles": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "json": {
      +          "type": "string"
      +        },
      +        "md": {
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "reportRound": {
      +      "type": "number"
      +    },
      +    "result": {},
      +    "round": {
      +      "type": "number"
      +    },
      +    "status": {
      +      "type": "string"
      +    },
      +    "taskId": {
      +      "type": "string"
      +    },
      +    "verificationSource": {
      +      "type": "string"
      +    },
      +    "zcodeSessionId": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observedv0.5.4

TDQS

B3.2/5.0
Behavior3/5

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

注释已提供 destructiveHint=true 和 readOnlyHint=false,描述未与之矛盾。描述补充了'同一 agent/项目与轮次记账'以及 feedback 的追加指示语义,这些是注释之外的有用信息。但未说明具体副作用(如是否会覆盖原有结果),对破坏性工具而言透明度中等。

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?

描述为单句,信息密度高,无冗余内容。虽然未使用分段或强调结构,但精炼且关键信息(状态限制、行为、反馈用途)均在前半句呈现,符合高效表达。

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?

工具简单(2个参数),且有输出 schema(未提供内容)。描述覆盖了核心操作和反馈语义,但未提及返回内容、可能的错误条件或前置条件(如是否需要先验收)。由于存在破坏性注释,缺少关于执行后影响的说明,完整性略逊。

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

Parameters2/5

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

Schema 描述覆盖率为 0%,描述需承担全部参数解释责任。描述明确解释了 feedback 作为'追加指示'并建议携带验收失败摘要,这对该参数提供了有用语义;但 taskId 仅从'终态任务'中隐含,未直接说明其标识作用,且未给出任何格式或示例。补偿不充分。

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?

描述以明确的动词'返修'指出了操作,并限定了资源(终态任务 failed/needs_attention)和行为(重新入队续跑),能够与兄弟工具如 run_task(启动新任务)和 continue_task(可能继续非终态任务)大致区分。但未显式提及与这些工具的差异,因此扣一分。

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

描述隐含了使用条件(当任务处于 failed 或 needs_attention 终态时),但未明确说明何时不应使用此工具,也未提及替代方案(如 verify_task 或 cancel_task)。使用情境可从状态限制推断,但缺少显式的 when-not 指导。

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