Skip to main content
Glama

Nexez Agentic Commerce

by ai.nexez
OverviewDiscussionsAdmin

Search Nexez offers

nexez_search
Read-only

Find services or products for a specific buyer request. Returns JSON text with ranked results, structured offers, listing slugs, agent.json URLs, and applied filters. Use nexez_directory for broad browsing, then nexez_get_page to inspect an exact offer before a dry run.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qYesWhat the buyer is looking for
latNoOptional latitude context metadata. Does not filter or rerank results; use location for geographic filtering.
lngNoOptional longitude context metadata. Does not filter or rerank results; use location for geographic filtering.
limitNoMaximum results; defaults to 10 and is rounded down and clamped to 1-50.
categoryNoMarketplace category; omit or use all to include both professional and consumer listings.
industryNoCase-insensitive substring filter on the published industry, for example plumbing.
locationNoOptional city/region filter
verifiedNoFilter by seller verification signal: true requires a signal, false requires its absence; omit to include both.
min_trustNoMinimum marketplace trust score (0-100); omit for no trust threshold. Not a guarantee of seller performance.
price_bandNoFilter by the listing marketplace price band. Inspect the exact offer for its price and currency; this is not a checkout quote.
min_readinessNoMinimum listing readiness score (0-100); omit for no readiness threshold.
supports_checkoutNoDeprecated compatibility filter: any actionable offer or provider handoff
nexez_checkout_readyNoOwner payout state confirms Nexez-settled checkout readiness
supports_negotiationNoFilter by negotiation availability: true for eligible listings, false for non-negotiable listings; omit to include both.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedInput schema / properties / category / description
      Added value: +"Marketplace category; omit or use all to include both professional and consumer listings."
    • addedInput schema / properties / industry / description
      Added value: +"Case-insensitive substring filter on the published industry, for example plumbing."
    • addedInput schema / properties / lat / description
      Added value: +"Optional latitude context metadata. Does not filter or rerank results; use location for geographic filtering."
    • changedInput schema / properties / limit / description
      Previous value: -"Max results (default 10)"New value: +"Maximum results; defaults to 10 and is rounded down and clamped to 1-50."
    • addedInput schema / properties / lng / description
      Added value: +"Optional longitude context metadata. Does not filter or rerank results; use location for geographic filtering."
    • addedInput schema / properties / min_readiness / description
      Added value: +"Minimum listing readiness score (0-100); omit for no readiness threshold."
    • addedInput schema / properties / min_trust / description
      Added value: +"Minimum marketplace trust score (0-100); omit for no trust threshold. Not a guarantee of seller performance."
    • addedInput schema / properties / price_band / description
      Added value: +"Filter by the listing marketplace price band. Inspect the exact offer for its price and currency; this is not a checkout quote."
    • addedInput schema / properties / supports_negotiation / description
      Added value: +"Filter by negotiation availability: true for eligible listings, false for non-negotiable listings; omit to include both."
    • addedInput schema / properties / verified / description
      Added value: +"Filter by seller verification signal: true requires a signal, false requires its absence; omit to include both."
  2. Changed2 schema fields changed
    • addedInput schema / properties / nexez_checkout_ready
      Added value: +{
+  "description": "Owner payout state confirms Nexez-settled checkout readiness",
+  "type": "boolean"
+}
    • addedInput schema / properties / supports_checkout / description
      Added value: +"Deprecated compatibility filter: any actionable offer or provider handoff"
  3. Changed8 schema fields changed
    • addedInput schema / properties / category
      Added value: +{
+  "enum": [
+    "all",
+    "professional",
+    "consumer"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / industry
      Added value: +{
+  "type": "string"
+}
    • addedInput schema / properties / min_readiness
      Added value: +{
+  "maximum": 100,
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / min_trust
      Added value: +{
+  "maximum": 100,
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / price_band
      Added value: +{
+  "enum": [
+    "free",
+    "under_100",
+    "100_500",
+    "500_2000",
+    "2000_plus",
+    "custom"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / supports_checkout
      Added value: +{
+  "type": "boolean"
+}
    • addedInput schema / properties / supports_negotiation
      Added value: +{
+  "type": "boolean"
+}
    • addedInput schema / properties / verified
      Added value: +{
+  "type": "boolean"
+}
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true and destructiveHint=false. The description adds non-obvious behavioral context by revealing the response is JSON text with ranked results, structured offers, listing slugs, agent.json URLs, and applied filters, which goes beyond the structured annotation fields.

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 with no filler: action, return-value summary, and routing guidance. The most important usage distinction is front-loaded without sacrificing clarity.

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?

With no output schema, the description compensates by enumerating the key return components and the intended workflow. It does not document the exact JSON structure or define ranking beyond 'ranked,' but it is sufficient for an agent to call the tool and interpret the response.

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?

The input schema has 100% parameter description coverage, so the description is not required to explain each parameter. It doesn't add substantive parameter semantics beyond the schema, landing at the baseline 3.

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

Purpose5/5

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

States a specific action and resource: 'Find services or products for a specific buyer request,' clearly distinguishing it from broad browsing via nexez_directory and exact-offer inspection via nexez_get_page. The verb and object are unambiguous.

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

Usage Guidelines5/5

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

Provides explicit routing: use nexez_directory for broad browsing, then nexez_get_page to inspect an exact offer before a dry run. This tells the agent when this search tool is appropriate relative to sibling tools.

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

All Nexez Agentic Commerce toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources