Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Session History

delimit_session_history
Read-onlyIdempotent

Load recent session handoffs to recover context at startup. Review completed items, key decisions, and blockers from previous runs to resume work where it stopped.

Instructions

Load recent session handoffs for context recovery.

When to use: at session start to see what previous sessions left — items completed, key decisions, blockers from the last N runs. When NOT to use: to write a handoff (use delimit_session_handoff) or for richer cross-model state (delimit_revive).

Sibling contrast: delimit_session_handoff writes; delimit_revive reads soul state; this reads structured handoffs.

Side effects: read-only. Calls ai.ledger_manager.session_history.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoNumber of recent sessions to return. Default 5.
ventureNoVenture to scope the snapshot to. Empty = auto-detect.
project_pathNoProject to scope the pending-receipts/dispatch/handoff snapshot to. Empty = aggregate.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv4.19.1
    • addedInput schema / properties / project_path
      Added value: +{
+  "default": "",
+  "description": "Project to scope the pending-receipts/dispatch/handoff snapshot to. Empty = aggregate.",
+  "type": "string"
+}
    • addedInput schema / properties / venture
      Added value: +{
+  "default": "",
+  "description": "Venture to scope the snapshot to. Empty = auto-detect.",
+  "type": "string"
+}
  2. Changed1 schema field changedv4.7.9
    • changedInput schema / properties / limit / description
      Previous value: -"Number of recent sessions to return (default 5)."New value: +"Number of recent sessions to return. Default 5."
  3. Addedv4.5.5

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, and the description reinforces with 'Side effects: read-only' and names the backend call ai.ledger_manager.session_history. It also clarifies it reads structured handoffs rather than soul state, adding context beyond the annotations, though it doesn't discuss error/ordering behavior.

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?

Front-loaded purpose, then clearly labeled when-to-use, when-not-to-use, sibling contrast, and side effects. A little redundancy exists between the when-not-to-use section and the sibling contrast paragraph, but every sentence earns its place and the structure makes scanning easy.

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?

Given a read-only, idempotent tool with a full input schema and output schema, the description covers purpose, use context, exclusions, and side effects. No critical behavioral or selection information is missing for an agent to call it correctly.

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?

Input schema has 100% description coverage with defaults for limit, venture, and project_path, so the baseline is 3. The description only loosely indicates 'last N runs' and doesn't add meaning beyond the schema's parameter documentation.

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 opens with a specific verb+resource: 'Load recent session handoffs for context recovery', then distinguishes from siblings: delimit_session_handoff writes, delimit_revive reads soul state, while this reads structured handoffs. An agent can tell this from nearby read/write snapshot tools.

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?

Explicit when-to-use (session start, surface items completed, key decisions, blockers from last N runs) and when-not-to-use with named alternatives (delimit_session_handoff for writes, delimit_revive for cross-model state). No ambiguity about selection.

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