Skip to main content
Glama

Liminal

handoff

Save or continue work across sessions. create: task, session_state, evidence, subject. resume: subject or handoff_id. list. More args: get_capabilities(tool=...).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>",
      "context": "<context>"
    },
    "name": "handoff"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskNo
actionYescreate|resume|list
contextYesUser's goal in one short sentence; no personal data or secrets.
subjectNowork name; resume by subject in one call
evidenceNo
llm_modelNoYour exact model id for analytics, or "unknown"; never guess.
handoff_idNo
session_stateNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
      -  "action",
      -  "context",
      -  "llm_model"
      -]New value: +[
      +  "action",
      +  "context"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / context / description
      Previous value: -"Describe the user's goal in one short sentence. Omit personal data and secrets."New value: +"User's goal in one short sentence; no personal data or secrets."
    • changedInput schema / properties / llm_model / description
      Previous value: -"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."New value: +"Your exact model id for analytics, or \"unknown\"; never guess."
  3. Changed2 schema fields changed
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "action",
      -  "context"
      -]New value: +[
      +  "action",
      +  "context",
      +  "llm_model"
      +]
  4. Changed24 schema fields changed
    • addedInput schema / properties / action / description
      Added value: +"create|resume|list"
    • removedInput schema / properties / action / title
      Removed value: -"Action"
    • removedInput schema / properties / checkpoint
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "additionalProperties": true,
      -      "type": "object"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Checkpoint"
      -}
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Describe the user's goal in one short sentence. Omit personal data and secrets.",
      +  "type": "string"
      +}
    • removedInput schema / properties / current_artifact_hash
      Removed value: -{
      -  "default": "",
      -  "title": "Current Artifact Hash",
      -  "type": "string"
      -}
    • removedInput schema / properties / detail
      Removed value: -{
      -  "default": "lean",
      -  "title": "Detail",
      -  "type": "string"
      -}
    • removedInput schema / properties / evidence / default
      Removed value: -""
    • removedInput schema / properties / evidence / title
      Removed value: -"Evidence"
    • removedInput schema / properties / handoff_id / default
      Removed value: -""
    • removedInput schema / properties / handoff_id / title
      Removed value: -"Handoff Id"
    • removedInput schema / properties / parent_handoff_id
      Removed value: -{
      -  "default": "",
      -  "title": "Parent Handoff Id",
      -  "type": "string"
      -}
    • removedInput schema / properties / refs
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "additionalProperties": true,
      -      "type": "object"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Refs"
      -}
    • removedInput schema / properties / resources
      Removed value: -{
      -  "default": "",
      -  "title": "Resources",
      -  "type": "string"
      -}
    • removedInput schema / properties / session_state / default
      Removed value: -""
    • removedInput schema / properties / session_state / title
      Removed value: -"Session State"
    • removedInput schema / properties / source_sessions
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "items": {
      -        "type": "string"
      -      },
      -      "type": "array"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Source Sessions"
      -}
    • removedInput schema / properties / subject / default
      Removed value: -""
    • addedInput schema / properties / subject / description
      Added value: +"work name; resume by subject in one call"
    • removedInput schema / properties / subject / title
      Removed value: -"Subject"
    • removedInput schema / properties / task / default
      Removed value: -""
    • removedInput schema / properties / task / title
      Removed value: -"Task"
    • removedInput schema / properties / tool_manifest
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "items": {
      -        "additionalProperties": true,
      -        "type": "object"
      -      },
      -      "type": "array"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Tool Manifest"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "action"
      -]New value: +[
      +  "action",
      +  "context"
      +]
    • removedInput schema / title
      Removed value: -"handoffArguments"
  5. First observed

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden, and it leaves the important traits unstated: whether create overwrites or appends, what happens when resume finds no matching subject/handoff_id, whether saved state is user-visible or retained, and what any action returns. Pointing to get_capabilities(tool=...) is the only behavioral aid offered.

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?

Very small and front-loaded, with the core statement first and action details after; nothing is padded. The telegraphic fragment style ('list.', 'resume: subject or handoff_id.') is efficient but edges toward being too clipped for a multi-action tool.

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?

For an 8-parameter, three-action tool with no annotations and no output schema, the description covers the action space but little else. The get_capabilities pointer partially offloads further detail, yet an agent still lacks enough to confidently author session_state/evidence payloads or interpret results.

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?

With 8 parameters at 50% schema coverage, the description does add value by grouping parameters under each action ('create: task, session_state, evidence, subject'), which the flat schema does not convey. But the two most consequential fields, session_state and evidence, get no meaning, format, or size guidance in either place, and llm_model is not addressed at all.

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?

Opens with a specific verb and scope: 'Save or continue work across sessions,' which tells an agent this is a cross-session persistence tool. The three action labels (create/resume/list) further pin the resource down. It never differentiates from the sibling list, but no sibling obviously overlaps, so the purpose is clear.

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?

The action breakdown effectively says which action goes with which identifier ('resume: subject or handoff_id'), which is a real invocation hint. However, there is no explicit when-to-use framing (e.g., call resume at session start, create before a long-running task) and no exclusions or conditions for picking this over another tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.