easypost_refund_shipmentRequest a refund (void) of a purchased shipping label. WARNING: reverses a purchase; approval depends on the carrier and label age. API: POST /shipments/{id}/refund.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Shipment id to refund, e.g. shp_... |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true. The description adds behavioral context beyond annotations by specifying that approval depends on carrier and label age, which is crucial for usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: first states purpose, second adds warning and API reference. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given simple tool with one parameter and no output schema, the description covers purpose, key behavioral caveats. However, missing information about return value or response format would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter 'id' with schema description 'Shipment id to refund, e.g. shp_...'. Schema coverage is 100%, so baseline 3. Description does not add extra parameter information beyond what schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Explicitly states 'Request a refund (void) of a purchased shipping label.' The verb 'request' and resource 'purchased shipping label' are specific and distinct from siblings like buy or create.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context: warning about reversing a purchase, carrier approval, and label age dependency. Does not explicitly list when not to use, but the warning implies conditions for success.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct purpose: address operations, shipment lifecycle (create, buy, refund, get, list), and tracking. No overlap or ambiguity.
All tools follow a consistent `easypost_<verb>_<resource>` pattern using snake_case, with clear verbs like create, get, list, buy, refund, verify.
11 tools cover the essential operations for address management, shipment lifecycle, and tracking without being too many or too few.
Core workflows (rate, buy, refund, track, address verification) are complete. Minor gaps like missing delete for addresses or update for shipments are acceptable for the domain.