get_returns_summaryAmazon returns over a window: total count, total units, and the top return reasons and dispositions.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Lookback window in days (default 30). |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": false,
+ "properties": {},
+ "type": "object"
+}Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds the window-based behavior and the output content (count, units, reasons, dispositions). However, it does not disclose any additional behavioral traits like data freshness, pagination, or edge cases. Given annotations, a 3 is appropriate as it adds some value but lacks rich behavioral context.
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 sentence that is front-loaded with the tool's purpose and output details. Every word earns its place, with no fluff or redundant information.
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 tool with one optional parameter and an output schema, the description sufficiently explains what the tool does and its primary outputs. It is not overly complex, and the output schema handles return value details. A slight gap is that it doesn't mention the default window, but that is covered by the schema. Overall, it is quite complete for its complexity.
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 input schema has one parameter 'days' with a complete description (lookback window, default 30). Schema coverage is 100%, so the baseline is 3. The description only vaguely references 'over a window' without adding new meaning beyond the schema, so it does not elevate the score.
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 function: it provides Amazon returns summary over a window, specifically listing total count, total units, and top return reasons and dispositions. This is a specific verb (get) + resource (returns summary) and distinguishes it from sibling tools like search_returns (detailed returns) or get_orders_summary.
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 for summary-level views of returns over a configurable window. It clearly communicates the context (summary over a window) but does not explicitly exclude alternatives or mention when to use other tools. This qualifies as 'clear context, no exclusions'.
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.