Skip to main content
Glama

rr_retry_recommendation_draft

DestructiveIdempotent

Retry creating a draft purchase order or draft transfer from a recommendation after a failed or blocked attempt; drafts only, nothing sent and no stock moved.

Instructions

Try again to turn a recommendation into its draft purchase order or draft transfer after an earlier attempt was blocked or failed. Same effects as rr_create_draft_from_recommendation: drafts only, nothing sent and no stock moved.

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_id": "<action_id>",
      "idempotency_key": "<idempotency_key>",
      "expected_updated_at": "<expected_updated_at>"
    },
    "name": "rr_retry_recommendation_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
action_idYesThe recommendation id, from rr_list_recommendations.
idempotency_keyYesA value you choose for this attempt. Repeating a call with the same value and the same arguments returns the first result and does nothing again.
expected_updated_atYesThe action's updated_at as last read (rr_preview_recommendation or rr_get_recommendation). The call is refused if the action changed since, so it can be read again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.3.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds the material context that the only effects are drafts — nothing sent, no stock moved — which directly informs risk assessment for a write tool. It does not say what a persistently failing retry returns or whether partial drafts can be left behind, so there is still a gap.

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?

Two tight sentences with the retry condition front-loaded and the safety scope immediately after; nothing is padding. It could be marginally sharper by naming the first-attempt tool as the actual alternative rather than only comparing effects.

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 3-parameter mutation tool with full schema coverage and a complete safety annotation set, the description covers when to call it, what it shares with its sibling, and its effect boundary. Without an output schema, more detail on what a successful retry returns or what happens on repeat failure would round it out.

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 coverage is 100% and all three parameters carry their own descriptions, including the meaning of idempotency_key and the stale-read guard on expected_updated_at. The description adds no parameter-level detail beyond that, so the baseline 3 is appropriate.

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?

States a specific verb-and-resource pair ('try again to turn a recommendation into its draft purchase order or draft transfer') plus the gating condition ('after an earlier attempt was blocked or failed'). It explicitly contrasts itself with rr_create_draft_from_recommendation, so an agent can separate retry from first attempt without opening either 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?

The precondition for use (a prior blocked or failed attempt) is stated unambiguously, and the sibling rr_create_draft_from_recommendation is named as the equivalent first-attempt path. It stops short of an explicit 'do not use this for a first attempt' instruction, but the context makes the routing clear.

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