delimit

Official

Overview Schema Source Related Servers Discussions Admin

Delimit Ledger Add

delimit_ledger_add

Capture work that should outlive the current session by adding tasks, bugs, features, decisions, or strategy items to a project ledger.

Instructions

Add a new item to a project's ledger.

When to use: to capture work that should outlive the current session — tasks, bugs, features, decisions, strategy items. When NOT to use: for governance-classed work (use delimit_gov_new_task) or quick conversation memory (delimit_memory_store).

Sibling contrast: delimit_ledger_update changes; delimit_ledger_done closes; this creates.

Side effects: writes a new ledger entry via ai.ledger_manager.add_item. Coerces tags / acceptance_criteria / tools_needed from comma strings to lists via _coerce_list_arg. LED-5658: an unrecognized venture with no real project directory behind it fails closed with {"error", "unknown_venture", "known_ventures"} rather than silently succeeding into an isolated, non-canonical store.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`tags`	No	Labels/tags (e.g. ["deploy-ready", "ship"] or "deploy-ready,ship").
`title`	Yes	What needs to be done. Required.
`ledger`	No	"ops" (tasks, bugs, features) or "strategy" (decisions, direction).	ops
`source`	No	Where this came from (session, consensus, focus-group, etc).	session
`context`	No	Background info an AI agent needs to work on this item.
`venture`	No	Project name or path. Empty = auto-detect from cwd.
`priority`	No	P0 (urgent), P1 (important), P2 (nice to have).	P1
`item_type`	No	task, fix, feat, strategy, consensus.	task
`worked_by`	No	Which AI model is working on this. Auto-detected if empty.
`description`	No	Details.
`tools_needed`	No	Delimit tools needed (e.g. "delimit_lint", "delimit_test_coverage").
`acceptance_criteria`	No	List of testable "done when" conditions (e.g. "tests pass", "coverage > 80%").
`estimated_complexity`	No	small, medium, or large.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv4.7.9Jun 9, 2026

changedInput schema / properties / title / description

Previous value: -"What needs to be done."New value: +"What needs to be done. Required."

changedInput schema / properties / venture / description

Previous value: -"Project name or path (e.g. \"my-project\", \"./path/to/project\"). Auto-detects if empty."New value: +"Project name or path. Empty = auto-detect from cwd."

Changed13 schema fields changedv4.5.5May 7, 2026

addedInput schema / properties / acceptance_criteria

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "List of testable \"done when\" conditions (e.g. \"tests pass\", \"coverage > 80%\")."
+}

addedInput schema / properties / context

Added value: +{
+  "default": "",
+  "description": "Background info an AI agent needs to work on this item.",
+  "type": "string"
+}

addedInput schema / properties / description / description
```
Added value: +"Details."
```

addedInput schema / properties / estimated_complexity

Added value: +{
+  "default": "",
+  "description": "small, medium, or large.",
+  "type": "string"
+}

addedInput schema / properties / item_type / description

Added value: +"task, fix, feat, strategy, consensus."

addedInput schema / properties / ledger / description

Added value: +"\"ops\" (tasks, bugs, features) or \"strategy\" (decisions, direction)."

addedInput schema / properties / priority / description

Added value: +"P0 (urgent), P1 (important), P2 (nice to have)."

addedInput schema / properties / source / description

Added value: +"Where this came from (session, consensus, focus-group, etc)."

addedInput schema / properties / tags

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Labels/tags (e.g. [\"deploy-ready\", \"ship\"] or \"deploy-ready,ship\")."
+}

addedInput schema / properties / title / description
```
Added value: +"What needs to be done."
```

addedInput schema / properties / tools_needed

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Delimit tools needed (e.g. \"delimit_lint\", \"delimit_test_coverage\")."
+}

addedInput schema / properties / venture / description

Added value: +"Project name or path (e.g. \"my-project\", \"./path/to/project\"). Auto-detects if empty."

addedInput schema / properties / worked_by

Added value: +{
+  "default": "",
+  "description": "Which AI model is working on this. Auto-detected if empty.",
+  "type": "string"
+}

First observedv0.1.0Mar 22, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses the side effect (writes via ai.ledger_manager.add_item), the list coercion for tags/acceptance_criteria/tools_needed, and a specific failure mode (unknown_venture fails closed with error payload). This goes well beyond the annotation profile.

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, front-loaded sections (purpose, when/when-not, sibling contrast, side effects) with no filler. Every sentence serves a purpose, including the failure-mode note which is directly actionable.

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?

For a 13-parameter tool with an output schema, the description covers the core usage, exclusions, side effects, and failure modes. It doesn't detail every parameter, but the schema handles that. Slightly less than perfect because it doesn't mention anything about the return value, though the output schema covers it.

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 baseline is 3. The description adds behavioral nuance for parameters (coercion to lists, venture auto-detection and failure behavior) that isn't in the schema, elevating it to 4.

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?

The description opens with 'Add a new item to a project's ledger' – a specific verb and resource. It also contrasts with siblings (delimit_ledger_update changes, delimit_ledger_done closes, this creates), clearly distinguishing its role.

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 states when to use ('to capture work that should outlive the current session') and when NOT to use, naming two alternative tools (delimit_gov_new_task, delimit_memory_store) and the sibling contrast. This gives an agent decisive routing guidance.

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

Deploy Server