Add or remove redirects. Money is integer minor units (cents). Calling this changes nothing: it returns a preview of what would change and a confirmation link. Only the merchant, on that page, can make it happen.
| Name | Required | Description | Default |
|---|---|---|---|
| add | No | Redirects to add; one for an old address that has one replaces it. | |
| remove | No | Old addresses whose redirect goes. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds real behavior beyond the annotations: the call is a preview-only no-op that returns a confirmation link, and the actual change is merchant-gated on that page. The declarative annotations (readOnlyHint=false, destructiveHint=false) can be reconciled with this if generating the confirmation state is the side effect. The irrelevant 'money is integer minor units' line adds confusion but not a direct contradiction.
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?
Purpose is correctly front-loaded, but the sentence 'Money is integer minor units (cents)' is pure noise for a redirects tool and earns no place. The remaining three sentences are tight, so the flaw is one stray sentence rather than overall bloat.
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?
For a write-intent tool with only two optional parameters and no output schema, the description covers the key gotcha an agent must know (no direct write, preview + confirmation link, merchant-gated). It omits sibling routing guidance, which is the main remaining gap.
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 description coverage is 100% and the schema documents add/remove richly, so the baseline is 3. The description adds nothing about the two parameters, and its money sentence is inapplicable to a redirect tool, so it neither helps nor compensates.
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?
The opening sentence 'Add or remove redirects' gives a specific verb (add/remove) and resource (redirects), which is enough to separate it from the sibling redirects_list. It stops short of explicitly naming or contrasting an alternative, so it is clear but not maximally differentiated.
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?
Usage is only implied: it manages redirects and describes the two-step workflow, but never states when to pick this over redirects_list or when a redirect should be added vs removed. Adequate but leaves routing to inference.
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.
