Ask the user to approve cancelling one of their open orders (hash from list_orders). Returns an approval link; the cancellation is signed by the user's wallet in the Epsilon app. Orders already filled cannot be cancelled.
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | optional reason shown to the user (≤ 140 chars) | |
| orderHash | Yes | EIP-712 order hash to cancel (0x-hex, 32 bytes) — from list_orders |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds real behavior beyond the annotations: this is two-phase (user must approve), it returns an approval link, and the actual cancellation is wallet-signed in the Epsilon app rather than executed immediately. Annotations cover the safety profile (destructiveHint=false, openWorldHint=true), so this extra flow context is the valuable part. Minor gap: no mention of whether the approval link expires.
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?
Three tight sentences with the user-approval requirement front-loaded, followed by the return value and the failure condition. Nothing is padded and nothing redundant is repeated.
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?
No output schema exists, and the description compensates by stating what is returned ('an approval link'). For a 2-param mutation with full annotation coverage this is close to complete; only the follow-up step after receiving the link is unspecified.
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?
Schema coverage is 100%, so both properties are already documented with format (0x-hex, 32 bytes) and length constraint. The description's 'hash from list_orders' merely restates the schema's provenance note, adding no new syntax or semantics.
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?
Specific verb+resource ('approve cancelling one of their open orders') with the approval-flow framing stated up front. It is immediately distinguishable from siblings like list_orders (source of the hash) and get_order (read of a single order).
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?
Gives the prerequisite provenance ('hash from list_orders') and an explicit exclusion ('orders already filled cannot be cancelled'). It stops short of naming what to use instead when an order isn't cancellable, so it's clear but not fully routed.
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.
