Skip to main content
Glama

Universal Agents

by ai.universalagents
OverviewDiscussionsAdmin

Request an intro call

request_intro
Read-only

Drafts an intro email to Universal Agents for the person you are helping, with a mailto link they can send. Sends nothing itself.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalNoWhat they want AI to change.
nameNoTheir name.
sizeNoRoughly how many people.
agencyNoTheir agency.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
toYes
bodyYes
sentYes
mailtoYes
subjectYes
agent_mayYesWhat an agent may do with this answer unsupervised: a level on the Universal Agents Delegation Map, 1 Tell to 7 Hands Off.
provenanceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "agent_may": {
+      "additionalProperties": false,
+      "description": "What an agent may do with this answer unsupervised: a level on the Universal Agents Delegation Map, 1 Tell to 7 Hands Off.",
+      "properties": {
+        "label": {
+          "type": "string"
+        },
+        "level": {
+          "type": "integer"
+        },
+        "note": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "level",
+        "label",
+        "note"
+      ],
+      "type": "object"
+    },
+    "body": {
+      "type": "string"
+    },
+    "mailto": {
+      "type": "string"
+    },
+    "provenance": {
+      "additionalProperties": false,
+      "properties": {
+        "accountable": {
+          "additionalProperties": false,
+          "properties": {
+            "contact": {
+              "type": "string"
+            },
+            "name": {
+              "type": "string"
+            },
+            "title": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "name",
+            "title",
+            "contact"
+          ],
+          "type": "object"
+        },
+        "answer_type": {
+          "enum": [
+            "code"
+          ],
+          "type": "string"
+        },
+        "authors": {
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "name": {
+                "type": "string"
+              },
+              "title": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "name",
+              "title"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "required": [
+        "answer_type",
+        "authors",
+        "accountable"
+      ],
+      "type": "object"
+    },
+    "sent": {
+      "const": false,
+      "type": "boolean"
+    },
+    "subject": {
+      "type": "string"
+    },
+    "to": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "sent",
+    "to",
+    "subject",
+    "body",
+    "mailto",
+    "provenance",
+    "agent_may"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with 'Sends nothing itself' plus the fact that the output is a mailto link the user sends. That is useful side-effect disclosure beyond the annotations, though it says nothing about permissions or data handling.

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?

Two short, front-loaded sentences with zero filler; the action comes first and the no-side-effect caveat second.

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 and full param coverage, the description only needs to establish purpose and side-effect behavior, which it does. The one remaining gap is explicit routing guidance against the sibling informational tools.

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 the schema already documents goal, name, size, and agency. The description adds only the framing that the draft is for 'the person you are helping', which is marginal context rather than new parameter meaning.

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 names a specific verb and artifact ('Drafts an intro email to Universal Agents') and adds the concrete output ('with a mailto link they can send'), so an agent knows exactly what the tool produces. It doesn't explicitly differentiate against the siblings (about_universal_agents, answer_faq, get_pricing), but the action is self-evidently distinct.

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

Usage Guidelines3/5

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

Usage is only implied via 'for the person you are helping', which hints at the context without stating when to reach for this tool versus answering a FAQ or pricing question. No explicit when-not or prerequisite guidance is given.

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

All Universal Agents toolsInspect
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