MyHairMail Agent Tools

Match a colour across wig brands

color_crossmatch

Read-onlyIdempotent

Closest equivalent colours in ONE target brand for a known colour from a DIFFERENT brand, using MyHairMail's cross-brand colour mapping. Answers 'what is my shade called in brand X' — relevant when a colour is discontinued or out of stock, or when a shopper knows their shade in one brand and is shopping another. Returns up to 3 matches ranked by similarity (closest > close > approximate) with short tone notes, and when available an example_in_stock_style + product_url in the target brand. Same-brand requests are refused. One source colour and one target brand per call; 'all brands' and wildcards are not supported. Unknown brand: supported_brands is returned. Terms: https://mcp.myhairmailtools.com/terms

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source_brand": "<source_brand>",
      "source_color": "<source_color>",
      "target_brand": "<target_brand>"
    },
    "name": "color_crossmatch"
  }
}

Input Schema

Name	Required	Description
`source_brand`	Yes	Brand of the known color, e.g. 'Jon Renau'
`source_color`	Yes	Color code or name, e.g. '12FS8' or 'Shaded Praline'
`target_brand`	Yes	Single brand to match into, e.g. 'Belle Tress'. Wildcards and 'all brands' are not supported.

Output Schema

Name	Required	Description	Default
`note`	No
`match`	Yes
`reason`	No
`matches`	No
`retailer`	Yes
`source_brand`	No
`source_color`	No
`target_brand`	No
`supported_brands`	No
`source_color_query`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 27, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "match": {
+      "type": "boolean"
+    },
+    "matches": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "example_in_stock_style": {
+            "type": "string"
+          },
+          "product_url": {
+            "type": "string"
+          },
+          "similarity": {
+            "enum": [
+              "closest",
+              "close",
+              "approximate"
+            ],
+            "type": "string"
+          },
+          "target_brand": {
+            "type": "string"
+          },
+          "target_color": {
+            "type": "string"
+          },
+          "tone_notes": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "target_brand",
+          "target_color",
+          "similarity",
+          "tone_notes"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "note": {
+      "type": "string"
+    },
+    "reason": {
+      "type": "string"
+    },
+    "retailer": {
+      "type": "string"
+    },
+    "source_brand": {
+      "type": "string"
+    },
+    "source_color": {
+      "type": "string"
+    },
+    "source_color_query": {
+      "type": "string"
+    },
+    "supported_brands": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "target_brand": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "match",
+    "retailer"
+  ],
+  "type": "object"
+}

First observedSep 26, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral content: refusal of same-brand requests, single-brand constraint, and the supported_brands fallback for unknown brands.

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

Conciseness4/5

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

Purpose is front-loaded and every sentence carries information (context, return shape, refusals, fallback, terms). It is dense but not padded, with only mild redundancy between the description and the target_brand schema wording.

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

Completeness5/5

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

Despite a rich output schema and full annotations, the description still closes the remaining gaps an agent needs: ranking scheme (closest > close > approximate), examples, refusal behavior, and the unknown-brand fallback. Nothing required to invoke it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so a 3 is the baseline. The description adds constraint semantics beyond the schema by clarifying that exactly one source colour and one target brand are accepted per call and that wildcards/'all brands' are rejected.

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 verb and resource ('closest equivalent colours in ONE target brand for a known colour from a DIFFERENT brand') and names the underlying capability (MyHairMail's cross-brand colour mapping). This is clearly distinguishable from the stock-oriented siblings check_stock and get_restock_eta.

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?

Gives clear triggering contexts: colour discontinued or out of stock, or a shopper who knows their shade in one brand shopping another. It also states exclusions (same-brand refused, one source colour/one target brand, no 'all brands' or wildcards), though it never explicitly routes to a named alternative tool.

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

All MyHairMail Agent Tools tools Inspect

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

Need Help?