ESQ Matching Engine

Start with a lawyer from the ESQ CoPilot directory

start_from_directory_profile

Read-onlyIdempotent

Use FIRST when the person names or pastes an ESQ CoPilot directory listing (directory.esqcopilot.com/attorney/...) or says they want help with a lawyer they were viewing, e.g. "help me check and contact Jeffrey Roy Hartmann, California bar 150013: https://directory.esqcopilot.com/attorney/jeffrey-hartmann-ca-150013". Finds that exact lawyer in the directory's own records (no web fetch, no similar-name substitute) and returns the lawyer's facts with sources and dates, what is unknown, the contact options, and the few questions still open. Do not run search_attorneys first when the exact listing is given. Looking at a listing is not an endorsement or a statement about availability. Records an anonymous count only. This is a listing service, not a lawyer referral service. No lawyer pays for placement or ranking of any kind.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_from_directory_profile"
  }
}

Input Schema

Name	Required	Description
`platform`	No	Which assistant the user chose on the listing, if they said so. Not consent to anything.
`attorney_id`	No	The lawyer's stable id, if known. When both are given they must name the same lawyer.
`profile_url`	No	The directory profile address the user came from, e.g. https://directory.esqcopilot.com/attorney/jeffrey-hartmann-ca-150013. Only directory.esqcopilot.com profile addresses are accepted; the page is never fetched.

Output Schema

Name	Required	Description	Default
`facts`	Yes
`notices`	Yes
`entry_id`	Yes
`unknowns`	Yes
`legal_aid`	Yes
`test_data`	No
`assessment`	Yes
`api_version`	Yes
`attribution`	Yes
`conversation`	Yes
`entry_version`	Yes
`contact_options`	Yes
`selected_lawyer`	Yes
`selection_notice`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 5, 2026

changedOutput schema / properties / contact_options / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "properties": {
-      "esq_introduction": {
-        "anyOf": [
-          {
-            "additionalProperties": {},
-            "properties": {
-              "delivery": {
-                "x-observed-types": [
-                  "string",
-                  "null"
-                ]
-              },
-              "delivery_note": {
-                "x-observed-types": [
-                  "string",
-                  "null"
-                ]
-              },
-              "eligible": {
-                "x-observed-types": [
-                  "boolean",
-                  "null"
-                ]
-              },
-              "next_action": {
-                "anyOf": [
-                  {
-                    "additionalProperties": {},
-                    "properties": {
-                      "public_contact": {
-                        "anyOf": [
-                          {
-                            "additionalProperties": {},
-                            "properties": {
-                              "note": {
-                                "x-observed-types": [
-                                  "string",
-                                  "null"
-                                ]
-                              },
-                              "phone": {
-                                "x-observed-types": [
-                                  "string",
-                                  "null"
-                                ]
-                              },
-                              "website": {
-                                "x-observed-types": [
-                                  "string",
-                                  "null"
-                                ]
-                              }
-                            },
-                            "type": "object"
-                          },
-                          {
-                            "type": "null"
-                          }
-                        ]
-                      },
-                      "say_to_user": {
-                        "x-observed-types": [
-                          "string",
-                          "null"
-                        ]
-                      },
-                      "tool": {
-                        "x-observed-types": [
-                          "string",
-                          "null"
-                        ]
-                      },
-                      "type": {
-                        "x-observed-types": [
-                          "string",
-                          "null"
-                        ]
-                      }
-                    },
-                    "type": "object"
-                  },
-                  {
-                    "type": "null"
-                  }
-                ]
-              },
-              "tool": {
-                "x-observed-types": [
-                  "string",
-                  "null"
-                ]
-              }
-            },
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "phone": {
-        "x-observed-types": [
-          "string",
-          "null"
-        ]
-      },
-      "profile_page": {
-        "x-observed-types": [
-          "string",
-          "null"
-        ]
-      },
-      "profile_page_message": {
-        "x-observed-types": [
-          "string",
-          "null"
-        ]
-      },
-      "separate_routes_note": {
-        "x-observed-types": [
-          "string",
-          "null"
-        ]
-      },
-      "website": {
-        "x-observed-types": [
-          "string",
-          "null"
-        ]
-      }
-    },
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": {},
+    "properties": {
+      "phone": {
+        "x-observed-types": [
+          "string",
+          "null"
+        ]
+      },
+      "profile_page": {
+        "x-observed-types": [
+          "string",
+          "null"
+        ]
+      },
+      "profile_page_message": {
+        "x-observed-types": [
+          "string",
+          "null"
+        ]
+      },
+      "separate_routes_note": {
+        "x-observed-types": [
+          "string",
+          "null"
+        ]
+      },
+      "website": {
+        "x-observed-types": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / harness_required

Removed value: -{
-  "x-observed-types": [
-    "boolean",
-    "null"
-  ]
-}

changedOutput schema / required

Previous value: -[
-  "api_version",
-  "entry_version",
-  "entry_id",
-  "selected_lawyer",
-  "selection_notice",
-  "assessment",
-  "facts",
-  "unknowns",
-  "contact_options",
-  "conversation",
-  "legal_aid",
-  "harness_required",
-  "attribution",
-  "notices"
-]New value: +[
+  "api_version",
+  "entry_version",
+  "entry_id",
+  "selected_lawyer",
+  "selection_notice",
+  "assessment",
+  "facts",
+  "unknowns",
+  "contact_options",
+  "conversation",
+  "legal_aid",
+  "attribution",
+  "notices"
+]

AddedNov 4, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the readOnly/idempotent/openWorld annotations it discloses several things the annotations cannot: no page fetch, no similar-name substitution, that unknowns are surfaced with sources and dates, that an anonymous count is recorded, and that the service is a listing service with no paid placement. The 'no web fetch' claim is consistent with openWorldHint=false, and the anonymous count is disclosed rather than hidden.

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?

The triage rule is front-loaded in the first clause, which is exactly what an agent needs, and the example clarifies the URL-plus-name pattern. The closing compliance sentences ('listing service, not a lawyer referral service', 'no lawyer pays for placement') are defensible but slightly expand the block beyond what is needed to invoke the tool.

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 the description need not enumerate return fields, yet it still summarizes them (facts with sources and dates, unknowns, contact options, open questions), and it covers the zero-required-parameter case adequately. The one gap is that among 23 siblings it never distinguishes this from get_attorney_profile, which is the nearest ambiguity an agent would face.

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 description coverage is 100%, so each parameter's meaning is already documented in the schema, including the both-must-match rule for attorney_id plus profile_url and the 'not consent' caveat on platform. The description adds only the general framing that the user 'names or pastes' a listing, which does not materially extend the parameter definitions.

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 names a specific verb and resource ('start from a pasted directory listing') and states precisely what the tool does with it: finds that exact lawyer in the directory's own records, with no web fetch and no similar-name substitute. It explicitly distinguishes itself from search_attorneys, so an agent can route without opening either schema.

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?

It states the triggering condition ('Use FIRST when the person names or pastes an ESQ CoPilot directory listing ... or says they want help with a lawyer they were viewing'), gives a concrete example, and names the when-not ('Do not run search_attorneys first when the exact listing is given'). That is explicit when/when-not/alternative guidance.

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

All ESQ Matching Engine 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?