Skip to main content
Glama

Export the recorded final delivery bundle

dsh_export_delivery

Copies a settled or validated historical delivery index, source snapshot and evidence into an allowed workspace directory, verifying artifact hashes and paths without rerunning acceptance or starting any model request.

Instructions

Copies a recorded delivery index, selected source snapshot and evidence to a new directory inside allowed workspace roots. It exports a settled live task or a validated persisted-history task when no live task exists. Historical export requires task/deliveryStage/index taskId and stageCount alignment and still validates every recorded artifact hash and path; it copies recorded source bytes only, never reruns acceptance, never recaptures the current workspace and starts no model request or runtime.

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": {
      "taskId": "<taskId>",
      "destination": "<destination>"
    },
    "name": "dsh_export_delivery"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskIdYes
destinationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.8

TDQS

A4/5.0
Behavior4/5

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

With readOnlyHint=false and destructiveHint=false already supplied, the description still adds substantial context: it writes only under allowed workspace roots, copies recorded source bytes, and never reruns acceptance, recaptures the workspace, or starts a model/runtime. What remains unstated is behavior when the destination already exists, which matters given idempotentHint=false. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first sentence, but the second is a long run-on stacking validation rules, copy semantics, and negative guarantees without separators. Every clause is largely informative, yet the density makes it hard to scan and some claims (no model request, no runtime) overlap.

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 two-parameter mutating export with no output schema, the definition covers scope, source validation, and negative side effects well. It leaves out what an agent gets back (destination path or manifest) and how destination collisions are handled, which are the notable remaining gaps.

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?

Schema description coverage is 0%, so the description must carry parameter meaning. It does constrain destination to paths inside allowed workspace roots and implies taskId must identify a task whose deliveryStage/index taskId/stageCount metadata align, but the reference to stageCount and deliveryStage fields that do not exist in the input schema adds ambiguity rather than clarity.

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 opening sentence names a specific verb (copies) and specific resources (recorded delivery index, source snapshot, evidence) into a new directory, which is distinct from read-oriented siblings like dsh_get_result or dsh_list_history. An agent can tell what this tool produces without opening the schema.

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

Usage Guidelines4/5

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

It gives a clear selection rule: export a settled live task, or a validated persisted-history task when no live task exists. That resolves the main ambiguity, but no sibling is named as an alternative for read-only inspection or for unfinished tasks, so the exclusion set is incomplete.

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