AI Commerce Intelligence

commerce_preflight

Read-only

ACE's flagship pre-purchase decision product. ACE Verdict remains APPROVE/REJECT/UNKNOWN while v5.0 preserves universal claims through explicit product identity and field-level source trust. Batch-refreshes up to five finalists, preserves conflicts/staleness/unverifiable claims, and never treats query wording as proof.

Input Schema

TableJSON Schema

Name	Required	Default
`query`	No
`claims`	No
`region`	No
`country`	No	US
`currency`	No
`language`	No
`max_price`	No
`min_price`	No
`providers`	No
`postal_code`	No
`candidate_ids`	No
`excluded_terms`	No
`finalist_limit`	No
`required_terms`	No
`preferred_terms`	No
`auto_compile_claims`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedSep 4, 2026

changedInput schema / properties / providers / items / enum

Previous value: -[
-  "shopify_global",
-  "amazon_creators"
-]New value: +[
+  "shopify_global",
+  "ebay_browse",
+  "amazon_creators"
+]

changedInput schema / properties / providers / maxItems
```
Previous value: -2New value: +3
```

Changed3 schema fields changedSep 3, 2026

addedInput schema / properties / language

Added value: +{
+  "maxLength": 35,
+  "type": "string"
+}

addedInput schema / properties / postal_code

Added value: +{
+  "maxLength": 24,
+  "type": "string"
+}

addedInput schema / properties / region

Added value: +{
+  "maxLength": 80,
+  "type": "string"
+}

Changed2 schema fields changedSep 1, 2026

addedInput schema / properties / auto_compile_claims

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

addedInput schema / properties / claims

Added value: +{
+  "items": {
+    "properties": {
+      "aliases": {
+        "items": {
+          "maxLength": 120,
+          "minLength": 1,
+          "type": "string"
+        },
+        "maxItems": 12,
+        "type": "array"
+      },
+      "attribute": {
+        "maxLength": 80,
+        "minLength": 1,
+        "type": "string"
+      },
+      "closed_world": {
+        "type": "boolean"
+      },
+      "id": {
+        "maxLength": 80,
+        "minLength": 1,
+        "type": "string"
+      },
+      "kind": {
+        "enum": [
+          "auto",
+          "number",
+          "text",
+          "boolean",
+          "exists"
+        ],
+        "type": "string"
+      },
+      "max_age_seconds": {
+        "exclusiveMinimum": 0,
+        "maximum": 315360000,
+        "type": "integer"
+      },
+      "operator": {
+        "default": "eq",
+        "enum": [
+          "eq",
+          "neq",
+          "gte",
+          "gt",
+          "lte",
+          "lt",
+          "contains",
+          "not_contains",
+          "exists"
+        ],
+        "type": "string"
+      },
+      "required": {
+        "default": true,
+        "type": "boolean"
+      },
+      "unit": {
+        "maxLength": 20,
+        "minLength": 1,
+        "type": "string"
+      },
+      "value": {
+        "anyOf": [
+          {
+            "maxLength": 240,
+            "type": "string"
+          },
+          {
+            "type": "number"
+          },
+          {
+            "type": "boolean"
+          }
+        ]
+      }
+    },
+    "required": [
+      "attribute"
+    ],
+    "type": "object"
+  },
+  "maxItems": 40,
+  "type": "array"
+}

Changed1 schema field changedSep 1, 2026

addedInput schema / properties / providers

Added value: +{
+  "items": {
+    "enum": [
+      "shopify_global",
+      "amazon_creators"
+    ],
+    "type": "string"
+  },
+  "maxItems": 2,
+  "type": "array"
+}

First observedSep 1, 2026

TDQS

B3/5.0

Behavior4/5

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

Annotations already provide readOnlyHint, openWorldHint, and destructiveHint, but the description adds meaningful behavior beyond those: verdicts stay APPROVE/REJECT/UNKNOWN, conflicts/staleness/unverifiable claims are preserved, and query wording is never treated as proof. This helps an agent understand key non-obvious behaviors, though it still doesn't fully disclose response structure or side-effect semantics. No annotation contradiction is present; 'batch-refreshes' reads as recomputation rather than state mutation.

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

Conciseness3/5

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

The description is only three sentences and avoids excessive padding, but the first sentence is branding ('ACE's flagship') and the second contains version-specific noise ('v5.0'). The most actionable operational behavior is in the final sentence, so it is not front-loaded. It could be tightened while preserving clarity.

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

Completeness2/5

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

For a tool with 16 undocumented parameters and no output schema, this description is insufficient for correct invocation. It provides high-level semantics around verdicts and finalists, but omits response format, how claims are structured, provider behavior, regional parameters, and relationship to sibling tools. The warning about query wording is valuable, but it doesn't compensate for the missing operational detail.

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

Parameters2/5

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

Schema coverage is 0%, so the description must compensate, but it only references 'finalists,' 'claims,' and 'query wording' at a high level. It leaves the meaning of region, providers, price bounds, candidate_ids, auto_compile_claims, excluded/required/preferred terms, and the claims sub-fields unexplained. An agent cannot reliably construct a valid request from this description alone.

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 identifies the tool as a pre-purchase decision product and names its output verdict values (APPROVE/REJECT/UNKNOWN), plus a batch-refresh behavior for up to five finalists. It is understandable, but it reads more like a product pitch than a crisp verb+resource statement and doesn't distinguish it from sibling tools such as ace_check.

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

Usage Guidelines2/5

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

The description gives context ('pre-purchase decision product') and mentions batch-refreshing finalists, but it never states when to use commerce_preflight versus alternative sibling tools. No exclusions or condition-based routing is provided despite a large sibling set including ace_check, compile_commerce_claims, product_discovery, and route_commerce_decision.

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

All AI Commerce Intelligence tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0

Disambiguation3/5

Most tools target distinct workflow stages (discovery, identity, claims, decision, referral), and the detailed descriptions help separate them. However, ace_check and commerce_preflight both expose ACE Verdict decisions, and verify_global_offer is an explicitly legacy alternative to commerce_preflight, so an agent can still misselect among the verification/decision tools.

Naming Consistency3/5

All names are readable snake_case, and action tools use a verb_object pattern while query/metadata tools use noun phrases. The split is not chaotic, but it is inconsistent (e.g., product_discovery vs resolve_product_identity), and the commerce_/commercial_ prefix variation adds a minor wrinkle.

Tool Count4/5

Fifteen tools is at the upper end of a well-scoped service and is reasonable for a broad commerce intelligence domain. The count feels slightly heavy because there are several descriptive/policy tools and at least one legacy overlap (verify_global_offer) that could be consolidated.

Completeness4/5

The set covers the core pre-purchase workflow: discovery, identity resolution, claim compilation, verification, recalls, merchant readiness, trust, referrals, and routing. Minor gaps exist, such as no explicit claim-management or decision-status retrieval separate from the decision products, but these do not create dead ends.

Resources

Need Help?