get_margin_configPer-product margin configuration used for P&L: COGS and platform-fee percentage, optionally per channel. Returns up to 25 rows.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max rows (default 25). |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description supplements the annotations by disclosing the row limit ('Returns up to 25 rows') and the configuration scope (COGS and platform-fee percentage per channel). It does not contradict the readOnlyHint and adds value beyond the structured safety flags.
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 a single, information-dense sentence that conveys purpose, content, and behavior without redundancy or filler.
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 simple read-only tool with one optional parameter and an output schema, the description provides adequate context by explaining the data type and row cap. It does not delve into pagination or ordering, but these are not necessary given the schema and annotations.
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 provides 100% coverage of the single 'limit' parameter, including its default and maximum. The description adds no additional parameter-specific guidance; the mention of 'per channel' refers to the data structure, not a query parameter, so it does not enhance parameter understanding.
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 identifies the resource (per-product margin configuration) and specifies its contents (COGS and platform-fee percentage, optionally per channel). It distinguishes this tool from sibling get_* tools by focusing on margin/cost models, not just generic analytics or P&L summaries.
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 phrase 'used for P&L' provides a clear context for when to use this tool, but it does not explicitly name alternative tools or exclusions. With many get_* siblings, more explicit differentiation would be helpful, but the context is sufficient.
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.
Most tools target distinct data points (e.g., get_analytics_summary vs get_brand_score). However, 'search' and 'search_catalog' have overlapping functionality and could cause confusion, and 'fetch' is a helper tied to 'search', adding minor ambiguity.
The majority use consistent verb_noun snake_case (e.g., get_inventory, list_stores). Exceptions like 'fetch' and 'search' (without object) break the pattern, but they are few.
43 tools is excessive for a data-retrieval-only API. Many get_* and search_* tools could be consolidated (e.g., search_catalog, search_inventory, search_orders are similar). The large number will overwhelm an agent.
The tool set is entirely read-only (get, search, list, fetch). There are no create, update, or delete tools, which is a critical gap for managing e-commerce operations. Agents can only view data, not act on it.