delimit

Official

Overview Schema Source Related Servers Discussions Admin

Delimit Gov New Task

delimit_gov_new_task

Create a governance-classed task with risk tier and scope, turning a 'gating required' verdict into an auditable record before performing gated work.

Instructions

Create a governance-classed task with risk tier and scope (Pro).

When to use: immediately after delimit_gov_evaluate returns a "gating required" verdict and you need a tracked, audit-bearing record before performing the gated work. The three-step pipeline is delimit_gov_new_task -> delimit_gov_run -> delimit_gov_verify; this is step one. When NOT to use: for free-form work tracking (use delimit_ledger_add), to perform the work itself (delimit_gov_run), or to verify a completed task (delimit_gov_verify).

Sibling contrast: delimit_ledger_add tracks general work items with no policy gating; this creates a governance-classed task with a risk tier and scope record that the run/verify steps operate on. delimit_gov_evaluate returns a verdict only; this materializes that verdict into a tracked task.

Side effects: gated by require_premium — unlicensed callers receive a license payload, no task created. On a licensed call, invokes backends.governance_bridge.new_task which writes a new task record keyed by a generated task_id into the governance task store; the record carries title, scope, risk_level, repo path, and creation timestamp. The response is routed through _with_next_steps so the returned dict carries orchestrator hints.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`repo`	No	Filesystem path to the repository. Default "." (cwd).	.
`scope`	No	Description of what the task covers. Required.
`title`	No	Short task title. Required (empty string is rejected).
`risk_level`	No	One of "low", "medium", "high", "critical". Default "medium". Drives later approval requirements.	medium

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv4.7.9Jun 9, 2026

addedInput schema / properties / repo / description

Added value: +"Filesystem path to the repository. Default \".\" (cwd)."

addedInput schema / properties / risk_level / description

Added value: +"One of \"low\", \"medium\", \"high\", \"critical\". Default \"medium\". Drives later approval requirements."

addedInput schema / properties / scope / description

Added value: +"Description of what the task covers. Required."

addedInput schema / properties / title / description

Added value: +"Short task title. Required (empty string is rejected)."

Changed3 schema fields changedv4.5.5May 7, 2026
- addedInput schema / properties / scope / default
```
Added value: +""
```
- addedInput schema / properties / title / default
```
Added value: +""
```
- removedInput schema / required
```
Removed value: -[
-  "title",
-  "scope"
-]
```
First observedv0.1.0Mar 22, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations are minimal (not read-only, not destructive), so the description carries the burden and delivers richly: licensing gating with unlicensed callers receiving a license payload and no task creation, backend write to backends.governance_bridge.new_task, persisted fields, and routing through _with_next_steps. This goes well beyond what annotations provide and does not contradict them.

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?

The description is organized into clear labeled sections: purpose, when to use, when not to use, sibling contrast, and side effects. It is longer than average but every section adds decision-relevant information, and the core purpose is front-loaded.

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 governance task-creation tool with an output schema present, the description covers the trigger condition, pipeline position, license gating, persistence side effects, and response routing. Nothing an agent needs to decide whether and how to invoke this tool 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. The description adds meaningful context beyond the schema: risk_level drives approval requirements, and title/scope are semantically required despite empty defaults being rejected. This extra behavioral meaning justifies above baseline.

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?

Description states a specific verb and resource: 'Create a governance-classed task with risk tier and scope'. It distinguishes itself from delimit_ledger_add, delimit_gov_evaluate, delimit_gov_run, and delimit_gov_verify, so an agent can immediately tell what this tool does relative to siblings.

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 when to use ('immediately after delimit_gov_evaluate returns a gating required verdict'), when NOT to use, and names the alternative tools for each excluded case. It also places the tool as step one of a three-step pipeline, leaving no ambiguity about placement.

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

Deploy Server