Browse or page through offers without a free-text query. Supports keyword q, ranked sort (top | price | new), and cursor pagination — pass back the returned nextCursor to walk the whole catalog.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Optional keyword filter. | |
| sort | No | Ranked order (default top). | |
| limit | No | 1..200 (default 50). | |
| cursor | No | Pagination cursor from a previous nextCursor. | |
| category | No | ||
| offerType | No |
Changes observed during successful MCP inspections.
Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / cursorAdded value: +{
+ "description": "Pagination cursor from a previous nextCursor.",
+ "type": "string"
+}Input schema / properties / limit / descriptionPrevious value: -"1..200 (default 50)"New value: +"1..200 (default 50)."Input schema / properties / qAdded value: +{
+ "description": "Optional keyword filter.",
+ "type": "string"
+}Input schema / properties / sortAdded value: +{
+ "description": "Ranked order (default top).",
+ "enum": [
+ "top",
+ "price",
+ "new"
+ ],
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes pagination behavior and return of nextCursor. It does not explicitly state that the operation is read-only, but that is implied by 'browse'. Additional context on permissions or side effects is absent but appropriate for a listing operation.
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?
Two sentences, no filler. The first sentence states purpose, the second lists supported features. Perfect front-loading and economy of words.
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 tool with 6 optional parameters and no output schema, the description is adequate but incomplete: it omits 'category' and 'offerType' filters and does not describe return format. Siblings require more context (e.g., 'create_offer') but for a browse tool, the description is minimally sufficient.
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 67% (4/6 parameters have descriptions). The description adds value for 'q', 'sort', and 'cursor' by explaining pagination mechanism, but does not mention 'category' or 'offerType' filters, which are undocumented in schema as well. Overall, contribution is marginal given schema already describes most parameters.
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: browsing offers with optional keyword and pagination. It distinguishes from siblings like 'get_offer' (single retrieval) and 'discover'. However, the phrase 'without a free-text query' is slightly confusing, as it then mentions keyword support.
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 explains how to use keyword, sort, and cursor pagination, and instructs to pass back nextCursor. It does not explicitly contrast with sibling tools (e.g., when to use 'discover' instead) or specify 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.