GleanMark Trademark Search

Search Marks That Sound Alike

phonetic_search

Read-onlyIdempotent

Finds trademarks whose whole mark sounds like the given mark, using Metaphone codes and trigram similarity with a whole-mark threshold. Because it compares entire marks, a multi-word mark that only contains a sound-alike word is not returned: for QUICK, KWIK REWARDS does not appear even though KWIK sounds like QUICK. An empty or short result does not show that no sound-alike marks exist and is not a clearance result; run_knockout_search is the conflict search.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No
`mark_text`	Yes	Trademark name to find sound-alike matches for
`include_dead`	No
`nice_classes`	No	Filter by Nice classes
`similarity_threshold`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`results`	Yes
`query_mark`	Yes
`total_found`	Yes
`search_method`	Yes
`open_in_gleanmark`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedJul 11, 2026
- addedOutput schema / properties / results / items / properties / detail_url
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / results / items / properties / owner_detail_url
```
Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}
```

Changed1 schema field changedMar 17, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "open_in_gleanmark": {
+      "type": "string"
+    },
+    "query_mark": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "properties": {
+          "filing_date": {
+            "type": "string"
+          },
+          "mark_name": {
+            "type": "string"
+          },
+          "nice_classes": {
+            "items": {
+              "type": "integer"
+            },
+            "type": "array"
+          },
+          "owner": {
+            "type": "string"
+          },
+          "registration_number": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "serial_number": {
+            "type": "string"
+          },
+          "similarity_method": {
+            "type": "string"
+          },
+          "similarity_score": {
+            "type": "number"
+          },
+          "status": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "search_method": {
+      "type": "string"
+    },
+    "total_found": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "query_mark",
+    "total_found",
+    "search_method",
+    "results"
+  ],
+  "type": "object"
+}

First observedFeb 19, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context beyond that: the whole-mark threshold behavior, the non-exhaustive nature of empty results, and the explicit disclaim that it is not a clearance search. These are meaningful additions that help the agent interpret results correctly.

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?

The description is dense but efficient. It front-loads the core purpose, then adds a critical limitation with an example, and closes with a direct routing to the correct alternative. Every sentence earns its place; no fluff or redundancy.

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 an output schema present, return format is covered. The description fully explains the search's scope, limitations, and interpretation of results, and provides an alternative. It does not detail each parameter (already partially in schema) but the behavioral guidance is strong. Given the tool's complexity and the sibling landscape, it is near-complete.

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 description coverage is only 40% (mark_text and nice_classes have descriptions). The description does not explain the other three parameters: limit, include_dead, and similarity_threshold. It mentions 'whole-mark threshold' conceptually but does not connect it to the similarity_threshold parameter or explain its range/default. The description does not compensate for the low schema coverage.

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?

The description states a specific verb ('Finds'), resource ('trademarks'), and the method (Metaphone codes + trigram similarity) with a precise scope (whole-mark comparison). It clearly distinguishes from siblings like get_similar_marks (broader similarity) and run_knockout_search (conflict search) by explaining what it does and does not do.

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?

Explicitly provides when-to-use and when-not-to-use: the whole-mark limitation is illustrated with a concrete example (QUICK vs KWIK REWARDS), and the description explicitly says an empty result is not a clearance result and names the alternative (run_knockout_search) as the conflict search. This is exemplary guidance.

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

All GleanMark Trademark Search 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?