Cria cupom de desconto na Nuvemshop. action: create. data = JSON com code, type (percentage|absolute|shipping), value, etc.
[Flattened action: create]
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| account | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate that the tool is not read-only (readOnlyHint=false), not idempotent, and not destructive. The description adds that it creates a coupon and provides a hint about the data structure. However, it does not disclose other important behaviors such as whether authentication is required, what happens on duplicate codes, or any rate limiting. The description is adequate but not detailed.
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?
The description is very concise: two sentences plus a minor note. The first sentence states the purpose, the second explains the data format. Every element earns its place with no redundancy or fluff. The structure is front-loaded and efficient.
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 the tool's low complexity (2 parameters, 1 required, no output schema) and the presence of basic annotations, the description provides a workable understanding. However, it lacks full parameter documentation (the 'account' field is not explained), no example JSON, and no information about response format or error states. The hint about data structure is helpful but incomplete.
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?
The schema defines 'data' as a string with no description, and 'account' as an optional string. The description adds value by explaining that 'data' should be a JSON containing fields like code, type (with enum values: percentage|absolute|shipping), and value. This partially compensates for the 0% schema coverage. However, the 'account' parameter remains undocumented, and the description does not provide a complete structure or example.
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 description clearly states the tool's purpose in Portuguese: 'Cria cupom de desconto na Nuvemshop' (Creates discount coupon in Nuvemshop). The verb 'create' and resource 'coupon' are explicit. The sibling list includes a generic 'nuvemshop_coupons' (likely read-only) and separate write tools for orders and products, so this tool is well-distinguished as the coupon creation endpoint.
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?
The description implies usage by stating 'action: create' and describing the input data, but it lacks explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites, when not to use it, or related tools such as 'nuvemshop_coupons' for reading or other write tools. The context is implied but not clearly differentiated.
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.
Many tools have overlapping functionality, especially the get/list pairs for customers, orders, and products which have identical descriptions except for the default action. The multiple order write tools (cancel, close, fulfill, etc.) also share the same underlying description, making it difficult for an agent to select the correct one.
Tool names mix patterns: some use simple <resource> (nuvemshop_categories), others use <resource>_<action> (nuvemshop_customers_get), and others use <resource>_write_<action> (nuvemshop_orders_write_cancel). The get/list split for customers, orders, and products is inconsistent with the categories tool which lacks such a split.
With 24 tools, the server has an excessive number for its scope. Many tools are redundant (e.g., separate get and list tools for each resource, and individual write tools for order status transitions). Consolidating these would reduce the count and improve usability.
The server covers the main e-commerce resources (categories, coupons, customers, orders, products) with read and write operations. However, there are gaps: no ability to create or delete customers, delete products, or delete coupons. The set is workable but not fully comprehensive.