Capable

Log touch

log_touch

Record a call, email, meeting or LinkedIn activity; link account_id, contact_id or opportunity_id (resolve IDs first). Check existing activity: source_touch_id reuses captured work and fills missing details; don't narrate routine duplicates. New work needs request_id + occurred_at for retries. sequence_action records an explicit step outcome; retry the same payload for pending tracking. Process captured meetings without another touch: propose_updates(source_touch_id) then review_proposed_updates.

When to use: After any meaningful interaction. commit_reviewed_updates often applies this from an approved review. Logging an email or call the system also collects? Pass its id (the Gmail message id, the call id) as external_id, so the sync and the agent land on one activity.

Example: Log a 45-min discovery call with Sarah at Acme yesterday — covered pain, impact, decision criteria.

Input Schema

Name	Required	Description
`type`	Yes	Defaults: call \| email \| meeting \| linkedin \| sms \| other. A workspace admin may rename or add values — see the live set in propose_updates' workspace.enum_values, or an admin's describe_schema.
`source`	No	Defaults: manual \| transcript_paste \| api \| mcp \| inbox_import \| calendar_import \| imported_csv \| scheduler \| recorder \| reply_io \| instantly. A workspace admin may rename or add values — see the live set in propose_updates' workspace.enum_values, or an admin's describe_schema.
`subject`	No	Short title of the activity (an email's subject line, a meeting's title); searchable and part of the duplicate fingerprint.
`summary`	No	Plain-text account of what happened or was discussed — the rep's notes for an unrecorded call; searchable together with the subject.
`direction`	No	Defaults: inbound \| outbound. A workspace admin may rename or add values — see the live set in propose_updates' workspace.enum_values, or an admin's describe_schema.
`account_id`	No	A uuid.
`contact_id`	No	A uuid.
`request_id`	No	A uuid.
`external_id`	No	The activity's id in the system it came from (a Gmail message id, a dialer call id). An activity this workspace already holds under that id is returned instead of logged again (duplicate_suppressed), with only its blank details filled from this call.
`occurred_at`	No	An ISO 8601 datetime.
`participants`	No	Email addresses of the people on the activity (sender or recipients, meeting attendees), stored as a flat list and matched by participant search.
`custom_fields`	No	Values for the workspace's custom touch fields, keyed by field key (see describe_schema); the reserved capable_sequence_action key is refused — use sequence_action.
`opportunity_id`	No	A uuid.
`sequence_action`	No	Requires outbound matching-channel evidence. Call attempts or LinkedIn requests hold the step and need follow_up_on; not_now pauses. Acceptance needs confirmation. Omitted outcome means completed.
`source_touch_id`	No	Reuse captured activity; fill missing facts only. Conflicts need explicit correction. Use instead of request_id.
`duration_minutes`	No	An integer ≥ 0.

Output Schema

Name	Required	Description	Default
`note`	No
`touch`	No
`account`	No
`sequence_tracking`	No
`duplicate_suppressed`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 24, 2026

removedInput schema / properties / duration_minutes / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "string"
-  }
-]

addedInput schema / properties / duration_minutes / type
```
Added value: +[
+  "number",
+  "string"
+]
```

addedInput schema / properties / external_id

Added value: +{
+  "description": "The activity's id in the system it came from (a Gmail message id, a dialer call id). An activity this workspace already holds under that id is returned instead of logged again (duplicate_suppressed), with only its blank details filled from this call.",
+  "type": "string"
+}

removedInput schema / properties / sequence_action / properties / step / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "string"
-  }
-]

addedInput schema / properties / sequence_action / properties / step / type
```
Added value: +[
+  "number",
+  "string"
+]
```

changedInput schema / properties / type / description

Previous value: -"Defaults: call | email | meeting | linkedin | other. A workspace admin may rename or add values — see the live set in propose_updates' workspace.enum_values, or an admin's describe_schema."New value: +"Defaults: call | email | meeting | linkedin | sms | other. A workspace admin may rename or add values — see the live set in propose_updates' workspace.enum_values, or an admin's describe_schema."

Changed1 schema field changedOct 20, 2026
- removedInput schema / $schema
```
Removed value: -"https://json-schema.org/draft/2020-12/schema"
```

Changed1 schema field changedOct 20, 2026

removedInput schema / properties / sequence_action / properties / follow_up_on / pattern

Removed value: -"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$"

Changed7 schema fields changedOct 19, 2026

removedOutput schema / $schema

Removed value: -"https://json-schema.org/draft/2020-12/schema"

removedOutput schema / additionalProperties
```
Removed value: -{}
```

changedOutput schema / properties / account / anyOf

Previous value: -[
-  {
-    "additionalProperties": {},
-    "properties": {
-      "current_arr_cents": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "id": {
-        "format": "uuid",
-        "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
-        "type": "string"
-      },
-      "lifecycle_stage": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "name": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      }
-    },
-    "required": [
-      "id"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "properties": {
+      "current_arr_cents": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "id": {
+        "format": "uuid",
+        "type": "string"
+      },
+      "lifecycle_stage": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "name": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "required": [
+      "id"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / sequence_tracking / additionalProperties
```
Removed value: -false
```

removedOutput schema / properties / sequence_tracking / properties / enrollment_id / pattern

Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"

removedOutput schema / properties / touch / additionalProperties
```
Removed value: -{}
```
removedOutput schema / properties / touch / propertyNames
```
Removed value: -{
-  "type": "string"
-}
```

Changed5 schema fields changedOct 9, 2026

changedInput schema / properties / sequence_action / description

Previous value: -"Completes a sequence step: {enrollment_id: uuid, step: the person's current step}; needs request_id, contact_id, occurred_at, direction 'outbound' and the step's channel as type."New value: +"Requires outbound matching-channel evidence. Call attempts or LinkedIn requests hold the step and need follow_up_on; not_now pauses. Acceptance needs confirmation. Omitted outcome means completed."

addedInput schema / properties / sequence_action / properties / follow_up_on

Added value: +{
+  "format": "date",
+  "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+  "type": "string"
+}

addedInput schema / properties / sequence_action / properties / outcome

Added value: +{
+  "description": "One of: completed | no_answer | left_voicemail | not_now | connection_requested | connection_accepted.",
+  "type": "string"
+}

addedInput schema / properties / source_touch_id

Added value: +{
+  "description": "Reuse captured activity; fill missing facts only. Conflicts need explicit correction. Use instead of request_id.",
+  "type": "string"
+}

addedOutput schema / properties / note
```
Added value: +{
+  "type": "string"
+}
```

First observedOct 6, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations, the description explains duplicate suppression via external_id, retry requirements for new work, source_touch_id reuse behavior, sequence_action outcome semantics, and the reserved custom_fields key. These details materially affect how the agent should call the tool and avoid duplicate activity.

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 description is front-loaded with purpose and is appropriately sized for a 16-parameter nested tool, including a concise example. Some instructions are packed into dense semicolon chains, which slightly reduces scanability.

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?

Given the complex schema, nested objects, annotations, and existing output schema, the description covers the key usage paths, duplicate/retry behavior, and sibling routing needed to invoke the tool correctly. Nothing essential appears missing.

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 all parameters are already documented structurally. The description adds useful semantics for critical parameters such as external_id, source_touch_id, request_id/occurred_at retries, and sequence_action, though it does not explain every parameter.

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 states a specific verb and resource: record a call, email, meeting, or LinkedIn activity, with account/contact/opportunity linkage. It distinguishes clearly from propose_updates and commit_reviewed_updates in context, but does not explicitly differentiate itself from the sibling record_meeting tool.

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 when-to-use guidance ('After any meaningful interaction'), tells the agent to check existing activity before logging, and names alternatives/paths for captured meetings, approved reviews, synced external activity, and duplicate suppression. The conditions for using source_touch_id versus request_id are also stated.

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

All Capable 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?