Skip to main content
Glama
serve-delivery-mcp

serve-delivery-mcp

by edtechniti

Cancel delivery

cancel_delivery
DestructiveIdempotent

Cancel an unfinished delivery by delivery ID, providing a reason and optional notes; confirm with the user first because a canceled delivery cannot be resumed.

Instructions

Cancel a delivery that hasn't finished. Confirm with the user first; a canceled delivery can't be resumed.

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": {
      "delivery_id": "<delivery_id>"
    },
    "name": "cancel_delivery"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNo
reasonNocx_canceled
delivery_idYesDelivery id returned by dispatch_robot

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the description is not carrying the full burden. It nevertheless adds real behavioral value beyond the annotations: the irreversibility ('a canceled delivery can't be resumed') and the human-confirmation requirement, neither of which is derivable from destructiveHint alone. It does not say what side effects occur (e.g., impact on the assigned robot or in-flight state), which keeps it from a 5.

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

Conciseness5/5

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

Two short sentences, front-loaded with the action and its scope, followed by the safety-critical constraint. Every clause carries independent weight: applicability, confirmation, irreversibility. No filler.

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 a destructive, open-world mutation with three parameters and no output schema, the description covers the two highest-stakes facts (irreversibility and confirmation) but leaves the reason/notes parameters and the post-cancellation effects unexplained. Adequate but with clear gaps for a destructive operation.

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

Parameters2/5

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

Schema description coverage is only 33% — only delivery_id carries an inline description. The description says nothing about the 'reason' enum (nine possible values with a default of cx_canceled) or the free-text 'notes' field, so the agent gets no help choosing a reason code or understanding that notes is optional supplementary context. With low coverage, the description was expected to compensate and does not.

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 description states a specific verb and resource ('Cancel a delivery') and adds a scope qualifier ('that hasn't finished') that tells the agent when the action is even applicable. Unlike any sibling (dispatch_robot, track_delivery, unlock_robot_bin), this is the only terminating operation, so the intent is unambiguous.

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 usage condition (delivery must not have finished) and an explicit procedural precondition ('Confirm with the user first'). What it lacks is an explicit statement of when not to use it, e.g., for completed deliveries the agent should presumably use track_delivery or list_deliveries instead, but no alternative is named.

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