Skip to main content
Glama
Praket7

agent-interop-runtime

by Praket7

handoff_create

Create a structured work handoff between coding agent sessions, preserving continuation state, evidence, changed files, risks, and unresolved questions for deterministic handover.

Instructions

Create a structured work handoff between exact native sessions. The durable record keeps every field; the bounded delivery packet preserves deterministic continuation state and explicit omissions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
risksYes
workIdYes
objectiveYes
nextActionNo
assumptionsNo
evidenceIdsYes
changedFilesYes
rollbackNotesNo
sourceSessionYes
latestValidationNo
continuationStateNo
acceptanceCriteriaYes
destinationSessionNo
repositoryRevisionNo
authorityBoundariesYes
unresolvedQuestionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.3.2
    • addedInput schema / properties / assumptions
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / continuationState
      Added value: +{
      +  "enum": [
      +    "not_started",
      +    "in_progress",
      +    "needs_completion",
      +    "likely_complete",
      +    "existing_behavior_broken"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / latestValidation
      Added value: +{
      +  "properties": {
      +    "command": {
      +      "type": "string"
      +    },
      +    "label": {
      +      "type": "string"
      +    },
      +    "observedAt": {
      +      "type": "string"
      +    },
      +    "outcome": {
      +      "enum": [
      +        "passed",
      +        "failed",
      +        "unknown"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "outcome"
      +  ],
      +  "type": "object"
      +}
    • addedInput schema / properties / nextAction
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / repositoryRevision
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / rollbackNotes
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. First observedv0.2.18

TDQS

C2.7/5.0
Behavior3/5

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

The description adds behavioral context beyond annotations by stating that the durable record keeps every field and the bounded delivery packet preserves deterministic continuation state and explicit omissions. This clarifies artifact-level behavior but does not address side effects, permission needs, or invalid-state handling. Annotations already signal a write operation, so the description supplements rather than contradicts them.

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?

The description is concise: two sentences with the primary purpose front-loaded. The second sentence adds useful behavioral detail but is dense and uses jargon that may reduce clarity. There is no wasted text, but the phrasing could be more accessible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex creation tool with 16 parameters, nested required objects, an enum, and no output schema, this description is materially incomplete. It does not explain the required fields, the distinction between the durable record and delivery packet, the continuationState enum values, or what the tool returns. The agent would need significant external documentation to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description provides no parameter-level explanations. With 16 parameters, 9 required, and a nested latestValidation object with an enum, the agent must infer meaning purely from parameter names. The description does nothing to compensate for the schema gap.

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?

The description opens with a specific verb and object ('Create a structured work handoff') and adds distinguishing detail about durable records and bounded delivery packets. It clearly separates the create operation from handoff_update_status and handoff_packet, though phrases like 'exact native sessions' and 'bounded delivery packet' could be more explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit guidance on when to use this tool versus siblings such as handoff_update_status or handoff_packet. Usage context is only implied by the tool name and the phrase 'between exact native sessions.' No alternatives or exclusions are mentioned.

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