Skip to main content
Glama

marketbasketanalysis-mcp

get_opportunities

List the merchant's ranked bundle / cross-sell opportunities mined from order history, with support / confidence / lift / revenue-weighted score. Use this when a merchant asks 'what are my top opportunities?', 'show me the best bundles I haven't published yet', or 'what should I prioritize?'. Pair with triage_opportunity to act on a specific one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax opportunities to return. Default 10, max 50.
statusNoFilter by opportunity status. Defaults to 'proposed' (untriaged).proposed

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It clearly signals a read-only 'List' operation, states the data source (order history), and reveals that results are ranked by support/confidence/lift/revenue-weighted score. It does not mention pagination or response envelope, but for a simple list tool this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each with a job: state the action and output, give usage triggers, and point to the companion tool. No redundancy or filler; the most important information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The schema covers both optional parameters, and the description explains the output's key metrics and provides usage guidance. It doesn't define the exact return object structure, but no output schema exists and the missing detail is unlikely to block a correct call. Overall adequate for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters (limit, status) are fully described in the schema (100% coverage), including defaults and constraints. The description itself adds no extra parameter detail, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('List') and a concrete resource ('ranked bundle / cross-sell opportunities mined from order history'), and it names the scoring dimensions. It does not explicitly contrast with sibling tools like get_recommendations, but the example merchant questions frame the intended use. This is a clear purpose, with only partial sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use triggers via merchant question examples ('what are my top opportunities?') and advises pairing with triage_opportunity to act on a specific item. It implies triage_opportunity is the alternative when action is needed, though it does not enumerate exclusions for other siblings. This is clear context with a partial alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Tools map largely one-to-one to distinct actions, and descriptions explicitly differentiate similar-looking pairs like get_recommendations vs. get_bundle_for_cart vs. find_substitutes. However, score_cross_sell vs. analyze_basket and get_rationale vs. explain_opportunity could still confuse an agent, since both score/explain overlapping concepts. Overall ambiguity is low but not zero.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: get_* for retrieval, explain_* for drill-downs, score_* for validations, and action verbs for state changes. No camelCase or mixed conventions are present, making the naming highly predictable.

Tool Count3/5

19 tools is on the heavy side for a single server and exceeds the typical 3–15 range, even though most tools have distinct purposes. The large count reflects a broad feature set covering recommendations, alerts, forecasting, reorder, returns, and weekly planning, but a few tools could be consolidated. It feels slightly bloated rather than egregiously so.

Completeness4/5

The surface covers the main discovery–evaluation–action workflow: recommend, score, explain, triage, plan, and forecast. Minor gaps exist—there is no direct tool for creating or editing a bundle outside of weekly-plan actions, and no catalog-browsing capability—but those are largely external concerns. The workflow is coherent with no major dead ends.