customer_product_historyRetrieve the products a specific customer has purchased, with pagination and optional fresh data, to review buying history for follow-up or reporting.
Products one client bought.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number, from 1 | |
| fresh | No | Skip the local cache | |
| page_size | No | Items per page, at most 100 | |
| customerId | Yes | Client id |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is fully covered without the description. The description adds nothing behavioral: no mention of pagination over the purchase history, no mention of the cache-bypass semantics implied by the `fresh` flag, and no hint at result ordering or volume.
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?
It is a single four-word fragment with no padding, so nothing is wasted. But brevity here comes from under-specification rather than discipline: the one sentence carries no front-loaded scope, return shape, or routing 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 four-parameter list tool with no output schema, the description leaves the agent unable to know what a record contains (a transaction, a product line, a summary?) or how results are ordered. Annotations cover safety, but the remaining gaps are meaningful for correct invocation.
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%, so customerId, page, page_size and fresh are all self-documented; the baseline of 3 applies. The description does not add meaning to any of them — notably it says nothing about whether results are paginated or what `fresh` changes.
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?
"Products one client bought" conveys a resource (products) and a scope (a single client), so an agent can broadly infer it lists a customer's purchase records. However it never states it is a list/history endpoint, never contrasts with plausible siblings like customer_visit_history or customer_cards, and the phrase is terse enough to be mistaken for a catalog lookup.
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?
There is no explicit when-to-use, when-not-to-use, or named alternative. The only implied guidance is that a customerId must be known, leaving the agent to guess how this differs from customer_visit_history or payment_rows.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.