Truvon

Show results with what you found

show_results

Idempotent

Show your user a search's results in one view with what you found on the web for each (a rating and where it comes from, the review count, a link, a one-line note). Optional, after find_local_businesses. Your additions are labeled as yours, never as Truvon's, and never change rank.

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": {
      "search_id": "<search_id>",
      "found": "<found>"
    },
    "name": "show_results"
  }
}

Input Schema

Name	Required	Description
`found`	Yes	What you found, one entry per result you have something for
`model`	No	Optional: the model you run on (for example claude-sonnet-5-5), kept with the provenance of this call. Leave it out if you do not know.
`search_id`	Yes	The search_id find_local_businesses returned (kept 24 hours)

Output Schema

Name	Required	Description
`query`	No	The need as read: what it matched on and the kind of business it calls for
`results`	Yes	The businesses that fit, best first, as the text lists them
`showing`	No	What the results are, in one line
`possible`	No	Businesses that may fit, as the text lists them under Possible
`search_id`	Yes	This search (srch_…), for report_outcome, show_results and refines
`next_cursor`	No	The cursor for the next page (more_results); none on the last page
`measured_from`	No	The point distances are measured from, and how it was found
`follow_ups_due`	No	Earlier outcomes due a follow-up with your user

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedNov 7, 2026

changedInput schema / properties / model / description

Previous value: -"Optional: the model you run on (for example claude-sonnet-5-5 or gpt-5.5), kept with this report's provenance so what each model reports can be weighed over time. Leave it out if you do not know."New value: +"Optional: the model you run on (for example claude-sonnet-5-5), kept with the provenance of this call. Leave it out if you do not know."

addedOutput schema / properties / measured_from

Added value: +{
+  "description": "The point distances are measured from, and how it was found",
+  "type": [
+    "object",
+    "null"
+  ]
+}

changedOutput schema / properties / possible / description

Previous value: -"Businesses that may fit, each saying why it is not a result"New value: +"Businesses that may fit, as the text lists them under Possible"

removedOutput schema / properties / possible / items / properties / listing

Removed value: -{
-  "description": "The address of its full record, in Markdown",
-  "type": "string"
-}

removedOutput schema / properties / possible / items / properties / match

Removed value: -{
-  "description": "Why it fits the need",
-  "type": "string"
-}

removedOutput schema / properties / possible / items / properties / open

Removed value: -{
-  "description": "Whether it is in business, from dated evidence",
-  "type": [
-    "object",
-    "null"
-  ]
-}

addedOutput schema / properties / query

Added value: +{
+  "description": "The need as read: what it matched on and the kind of business it calls for",
+  "type": "object"
+}

changedOutput schema / properties / results / description

Previous value: -"The businesses that fit, best first"New value: +"The businesses that fit, best first, as the text lists them"

removedOutput schema / properties / results / items / properties / listing

Removed value: -{
-  "description": "The address of its full record, in Markdown",
-  "type": "string"
-}

removedOutput schema / properties / results / items / properties / match

Removed value: -{
-  "description": "Why it fits the need",
-  "type": "string"
-}

removedOutput schema / properties / results / items / properties / open

Removed value: -{
-  "description": "Whether it is in business, from dated evidence",
-  "type": [
-    "object",
-    "null"
-  ]
-}

Changed1 schema field changedNov 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "follow_ups_due": {
+      "description": "Earlier outcomes due a follow-up with your user",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "next_cursor": {
+      "description": "The cursor for the next page (more_results); none on the last page",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "possible": {
+      "description": "Businesses that may fit, each saying why it is not a result",
+      "items": {
+        "properties": {
+          "listing": {
+            "description": "The address of its full record, in Markdown",
+            "type": "string"
+          },
+          "match": {
+            "description": "Why it fits the need",
+            "type": "string"
+          },
+          "name": {
+            "description": "The business's name",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "open": {
+            "description": "Whether it is in business, from dated evidence",
+            "type": [
+              "object",
+              "null"
+            ]
+          },
+          "truvon_id": {
+            "description": "Its Truvon ID (biz_…), the business argument of get_business_record and report_outcome",
+            "type": "string"
+          }
+        },
+        "required": [
+          "truvon_id",
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "results": {
+      "description": "The businesses that fit, best first",
+      "items": {
+        "properties": {
+          "listing": {
+            "description": "The address of its full record, in Markdown",
+            "type": "string"
+          },
+          "match": {
+            "description": "Why it fits the need",
+            "type": "string"
+          },
+          "name": {
+            "description": "The business's name",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "open": {
+            "description": "Whether it is in business, from dated evidence",
+            "type": [
+              "object",
+              "null"
+            ]
+          },
+          "truvon_id": {
+            "description": "Its Truvon ID (biz_…), the business argument of get_business_record and report_outcome",
+            "type": "string"
+          }
+        },
+        "required": [
+          "truvon_id",
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "search_id": {
+      "description": "This search (srch_…), for report_outcome, show_results and refines",
+      "type": "string"
+    },
+    "showing": {
+      "description": "What the results are, in one line",
+      "type": "string"
+    }
+  },
+  "required": [
+    "search_id",
+    "results"
+  ],
+  "type": "object"
+}

AddedNov 7, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations say readOnlyHint=false, idempotent=true, destructive=false, but the description adds the non-obvious behavioral guarantees an agent actually needs: caller-supplied content is attributed to the caller, never to Truvon, and it never affects result ranking. It doesn't state persistence or latency, but the attribution/rank-invariance clauses are the important disclosures here.

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?

Two sentences, with the core action front-loaded before the parenthetical detail. The field parenthetical is somewhat list-like and redundant against the schema, but no sentence is wasted.

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?

An output schema exists, so return shape need not be explained, and the schema fully covers the three parameters including the 24-hour search_id window and maxItems. Combined with the attribution and rank-invariance notes, an agent has enough to call this correctly; only the relationship to sibling display tools is left implicit.

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?

Schema coverage is 100%, so every parameter including the nested found[] fields is already documented, establishing a baseline of 3. The description's parenthetical ("a rating and where it comes from, the review count, a link, a one-line note") merely restates those schema fields and adds nothing about search_id, model, or the 10-item cap.

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?

States a concrete verb and resource — showing a search's results in one view, enriched with per-result rating, source, review count, link, and note. It names its upstream sibling (find_local_businesses) but does not distinguish itself from more_results, answer_follow_up, or note_choice, so an agent must infer the boundary.

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 an explicit sequencing/when-to-use cue: "Optional, after find_local_businesses." The word "Optional" correctly signals it is not mandatory to complete a search. No when-not conditions or named alternatives are given, keeping it just below a 5.

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

All Truvon 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?