noticed

add_to_network

Idempotent

Add someone to your network. Known (e.g. a search_people hit) → tracked; new → created/imported + tracked. Accepts person_id OR free_form:{name,…} + optional tags and relationship_types (how you know them — set it right here at add time, no follow-up update_person needed). Returns canonical person_id. DEDUPE: a new free_form contact that strongly matches someone you already have returns { created:false, potential_duplicates, confirmation_token } instead of creating — track the existing person, or re-call with the confirmation_token only if it's genuinely someone new. relationship_types passed on a call that returns potential_duplicates are NOT kept — re-supply them on the follow-up call.

Input Schema

Name	Required	Description
`tags`	No	Initial tags to apply. Prefer an existing tag from your network over coining a near-duplicate (reuse `sf`, don't add `san-francisco`); lowercase, and use the event:/place:/topic: namespaces where they fit.
`free_form`	No	A brand-new contact to create + track. Use when there is no person_id.
`person_id`	No	person_id of an existing search_people hit to start tracking.
`custom_name`	No	Your own display name for this person.
`confirmation_token`	No	From a prior potential_duplicates response — pass it back to create despite the flagged duplicates (only after the user confirms it's a new person).
`relationship_types`	No	How you know this person, from the closed set: family, close_friend, friend, acquaintance, coworker, alumni, customer, vendor, advisor, investor. Values outside this set are dropped. Coworker and Alumni may be inferred from reliable shared history; all other roles require an explicit user statement. Set it here at add time — no follow-up update_person needed.

Output Schema

Name	Required	Description
`ok`	Yes	Whether noticed completed the operation.
`data`	No	The operation result when ok is true.
`error`	No	A human-readable error when ok is false.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 11, 2026

changedInput schema / properties / relationship_types / description

Previous value: -"How you know this person, from the closed set: family, close_friend, friend, coworker, ex_coworker, advisor_investor, customer, vendor, acquaintance. Values outside this set are dropped. Set it here at add time — no follow-up update_person needed."New value: +"How you know this person, from the closed set: family, close_friend, friend, acquaintance, coworker, alumni, customer, vendor, advisor, investor. Values outside this set are dropped. Coworker and Alumni may be inferred from reliable shared history; all other roles require an explicit user statement. Set it here at add time — no follow-up update_person needed."

Changed1 schema field changedAug 22, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "description": "The operation result when ok is true.",
+      "properties": {
+        "confirmation_token": {
+          "type": "string"
+        },
+        "created": {
+          "type": "boolean"
+        },
+        "person_id": {
+          "type": "string"
+        },
+        "potential_duplicates": {
+          "items": {
+            "additionalProperties": true,
+            "properties": {
+              "company": {
+                "$ref": "#/properties/data/properties/potential_duplicates/items/properties/person_id"
+              },
+              "display_name": {
+                "type": "string"
+              },
+              "headline": {
+                "$ref": "#/properties/data/properties/potential_duplicates/items/properties/person_id"
+              },
+              "id": {
+                "type": "string"
+              },
+              "name": {
+                "type": "string"
+              },
+              "person_id": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
+    "error": {
+      "description": "A human-readable error when ok is false.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether noticed completed the operation.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

First observedAug 22, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations establish the safety profile (not read-only, not destructive, idempotent), and the description adds substantial behavior on top: the dedupe short-circuit returns `{ created:false, potential_duplicates, confirmation_token }` instead of creating, and relationship_types supplied on a dedupe-flagged call are discarded and must be re-supplied. Those are non-obvious side effects an agent would otherwise stumble into.

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 definition is front-loaded and dense with zero filler sentences — the known-vs-new rule comes first, then the dedupe caveat, which is the right priority order. It loses a point for repetition: "set it right here at add time, no follow-up update_person needed" appears in both the description and the relationship_types schema text, and the DEDUPE block is written in compressed shorthand that takes a second read.

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?

For a mutation tool with six optional parameters, a nested free_form object, and an output schema, the description covers the things an agent must know before calling: which identity path to take, what dedupe returns, and how to recover from it. Return-value shape is delegated correctly to the output schema.

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 the baseline is 3, but the description adds real semantics the schema cannot express: person_id and free_form are described as mutually exclusive alternatives ("Accepts person_id OR free_form"), which the schema's flat additionalProperties:false does not enforce or communicate. It also clarifies that relationship_types is set at add time and saved without a second call, though it largely restates the closed-set rule already documented in the schema.

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?

"Add someone to your network" states a specific verb and resource, and the description immediately splits the operation into two concrete modes: known person (person_id → tracked) and new person (free_form → created/imported + tracked). That two-path framing tells an agent exactly what the tool does and how it differs from siblings like update_person or search_people.

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 gives explicit routing rules: use person_id when you have a search_people hit, use free_form when there is no person_id, and set relationship_types at add time rather than follow-up with update_person. It also states the when-not path for creation — if you get potential_duplicates, track the existing person instead of re-calling, and only re-call with confirmation_token after user confirmation.

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

All noticed 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?