Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Ledger Link

delimit_ledger_link

Create typed relationships between ledger items to track dependencies, hierarchy, or duplicates—such as blocks, parent/child, or relates_to—so both linked items reflect the connection.

Instructions

Create a typed relationship between two ledger items.

When to use: to track dependencies and structure (blocks, parent/child, duplicates) between ledger items. When NOT to use: to read existing links (use delimit_ledger_links) or update other fields (delimit_ledger_update).

Sibling contrast: delimit_ledger_links reads; delimit_ledger_update changes simple fields; this writes a relationship.

Side effects: writes the link via ai.ledger_manager.link_items. "blocks" / "blocked_by" auto-create the reverse direction so both items see the relationship. 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
NameRequiredDescriptionDefault
noteNoOptional note explaining the relationship.
to_idYesTarget item id (e.g. "STR-005"). Required.
from_idYesSource item id (e.g. "LED-025"). Required.
ventureNoProject name/path. Empty = auto-detect.
link_typeNoOne of "blocks" (default), "blocked_by", "parent", "child", "relates_to", "duplicates".blocks

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv4.7.9
    • changedInput schema / properties / from_id / description
      Previous value: -"Source item ID (e.g. \"LED-025\")."New value: +"Source item id (e.g. \"LED-025\"). Required."
    • changedInput schema / properties / link_type / description
      Previous value: -"Relationship type - \"blocks\", \"blocked_by\", \"parent\", \"child\", \"relates_to\", \"duplicates\"."New value: +"One of \"blocks\" (default), \"blocked_by\", \"parent\", \"child\", \"relates_to\", \"duplicates\"."
    • changedInput schema / properties / to_id / description
      Previous value: -"Target item ID (e.g. \"STR-005\")."New value: +"Target item id (e.g. \"STR-005\"). Required."
    • changedInput schema / properties / venture / description
      Previous value: -"Project name or path. Auto-detects if empty."New value: +"Project name/path. Empty = auto-detect."
  2. Addedv4.5.5

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only state readOnlyHint=false and destructiveHint=false. The description goes well beyond that by disclosing the concrete write path (ai.ledger_manager.link_items), the auto-reverse behavior for 'blocks'/'blocked_by' so both items see the relationship, and the LED-5658 fail-closed error format for unrecognized ventures. This is rich, actionable behavioral context.

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?

Well-structured with labeled sections (when to use, when NOT, sibling contrast, side effects) and a front-loaded purpose sentence. Minor redundancy: the sibling contrast paragraph partially restates the when-NOT-to-use section, and the LED-5658 note is verbose, though it does carry real 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 5-parameter write tool with an output schema, this description covers everything needed to call it correctly: purpose, selection criteria vs. two siblings, side effects, bidirectional link behavior, and a known edge-case error mode. No critical information an agent needs 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 genuine value beyond the schema by explaining that link_type 'blocks'/'blocked_by' auto-create the reverse direction, and by specifying the venture parameter's failure-mode behavior (unknown_venture error with known_ventures payload). This elevates it 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?

Opens with a specific verb+resource: 'Create a typed relationship between two ledger items.' It then explicitly contrasts itself with delimit_ledger_links (reads) and delimit_ledger_update (changes simple fields), so an agent can distinguish it from the closest siblings without opening 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?

Provides explicit 'When to use' (dependencies/structure: blocks, parent/child, duplicates) and 'When NOT to use' with named alternatives (delimit_ledger_links for reading, delimit_ledger_update for other fields). The sibling contrast section reinforces the routing decision with zero ambiguity.

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