task-checkpoint

Overview Schema Source Related Servers Discussions Admin

tc_init

Create a new tracked task for long-running coding or documentation work; any active task is suspended, not closed, so checkpoints can save progress and resume later.

Instructions

创建任务。已有活动任务会挂起而不是关闭。

Input Schema

TableJSON Schema

Name	Required	Description
`goal`	No	任务目标
`name`	Yes	任务名
`root`	Yes	工作区根目录
`store`	No	存档目录；省略时用工作区内 .checkpoints
`exclude`	No	额外的排除模式，按单个名字段匹配（目录名或路径第一段），如 ["config", "*.local"]
`constraints`	No	约束

Output Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	任务名
`note`	Yes	存档位置提示
`store`	Yes	存档目录
`exclude`	No
`task_id`	Yes	新任务 id
`prev_suspended`	No
`store_is_external`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.1.7Sep 30, 2026

addedInput schema / properties / exclude

Added value: +{
+  "description": "额外的排除模式，按单个名字段匹配（目录名或路径第一段），如 [\"config\", \"*.local\"]",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / exclude

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

First observedv0.1.1Sep 26, 2026

TDQS

A3.5/5.0

Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose one important side effect: existing active tasks are suspended, not closed. It says nothing about persistence, error conditions, or whether the store directory is created, leaving notable behavioral gaps for a stateful mutation tool.

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 with zero filler; the primary action is front-loaded and the behavioral note follows immediately. Nothing could be removed without losing information.

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?

The output schema exists and the schema fully documents parameters, so those burdens are lifted. What remains missing is routing context against the nine sibling tools and any note on required permissions or task-state preconditions, making it only minimally adequate given the tool's stateful nature.

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%, so all six parameters (goal, name, root, store, exclude, constraints) are already documented in the schema. The description adds no syntax, defaults, or format guidance beyond that, matching the baseline of 3.

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 and resource (创建任务 / create task), which is unambiguous. However, it never contrasts itself against siblings such as tc_switch or tc_resume, so an agent must infer the distinction from the name alone.

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?

Usage is implied rather than stated: it is the creation entry point, and the note that active tasks are suspended rather than closed hints at the interaction with tc_switch. There is no explicit when-to-use, when-not-to-use, or named alternative.

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

Deploy Server