ErzyCall

update_whatsapp_agent

Update the exact WhatsApp agent after reading it and confirming the selected account, agent, and exact changes. Explain activation, new-chat/contact behavior, audience/capability changes, and cleared text/arrays. For autoMarkMessagesRead, omission preserves the current value; false disables both Meta read receipts and typing while AI replies continue, but does not guarantee linked-client notifications. Resolve group IDs using list_contact_groups. Omitted fields stay unchanged. Requires fresh whatsapp_agents:write consent. Reuse the same idempotencyKey, updates, and expectedRevision on retry; on REVISION_CONFLICT, read and propose again. Read back after success. Saving affects future turns and sends no message.

Input Schema

TableJSON Schema

Name	Required	Description
`agentId`	Yes
`updates`	Yes
`confirmed`	Yes	Must be true only after the user explicitly confirms this exact operation
`idempotencyKey`	Yes	A unique identifier generated once for this intended write. Reuse exactly when retrying.
`expectedRevision`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No
`success`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 18, 2026

addedInput schema / properties / updates / properties / mcpOAuthConnectionIds

Added value: +{
+  "description": "MCP OAuth connectors enabled for this agent. All currently approved tools from these connectors are available automatically; approve individual tools in WA Settings. Replaces the connector selection when provided; omit to preserve it.",
+  "items": {
+    "maxLength": 100,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 50,
+  "type": "array"
+}

Changed1 schema field changedOct 16, 2026

changedInput schema / properties / updates / properties / allowedTools / items / enum

Previous value: -[
-  "request_human_decision",
-  "handle_human_request",
-  "get_contact_profile",
-  "get_organization_contact_count",
-  "get_recent_whatsapp_questions",
-  "get_contact_group_directory"
-]New value: +[
+  "request_human_decision",
+  "handle_human_request",
+  "get_contact_profile",
+  "get_organization_contact_count",
+  "get_recent_whatsapp_questions",
+  "get_contact_group_directory",
+  "get_my_lessons",
+  "get_today_lessons",
+  "render_week_calendar"
+]

Changed2 schema fields changedOct 14, 2026

addedInput schema / properties / updates / properties / autoMarkMessagesRead

Added value: +{
+  "description": "Whether ErzyCall sends Meta read receipts for inbound messages. Omitting this field from an update preserves the current stored value; legacy configurations where it is unset behave as enabled. Set false to disable both the read receipt and coupled typing indicator while AI processing and replies continue; this does not guarantee notifications on linked clients.",
+  "type": "boolean"
+}

changedInput schema / properties / updates / properties / model / enum

Previous value: -[
-  "claude-sonnet-5",
-  "claude-haiku-4-5",
-  "gpt-6-luna",
-  "gpt-6.1-sol"
-]New value: +[
+  "claude-sonnet-5",
+  "claude-haiku-5-5",
+  "claude-haiku-4-5",
+  "gpt-6-luna",
+  "gpt-6.1-sol"
+]

Changed1 schema field changedOct 8, 2026

changedInput schema / properties / updates / properties / allowedTools / items / enum

Previous value: -[
-  "get_contact_profile",
-  "get_organization_contact_count",
-  "get_recent_whatsapp_questions",
-  "get_contact_group_directory"
-]New value: +[
+  "request_human_decision",
+  "handle_human_request",
+  "get_contact_profile",
+  "get_organization_contact_count",
+  "get_recent_whatsapp_questions",
+  "get_contact_group_directory"
+]

Changed1 schema field changedOct 7, 2026
- removedInput schema / properties / updates / properties / externalToolIds / maxItems
```
Removed value: -100
```

Changed1 schema field changedOct 7, 2026

changedInput schema / properties / updates / properties / model / enum

Previous value: -[
-  "claude-sonnet-5",
-  "claude-haiku-4-5"
-]New value: +[
+  "claude-sonnet-5",
+  "claude-haiku-4-5",
+  "gpt-6-luna",
+  "gpt-6.1-sol"
+]

Changed1 schema field changedOct 7, 2026

addedInput schema / properties / updates / properties / externalToolIds

Added value: +{
+  "items": {
+    "maxLength": 100,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "type": "array"
+}

Changed1 schema field changedOct 6, 2026

changedInput schema / properties / updates / properties / model / enum

Previous value: -[
-  "claude-haiku-4-5"
-]New value: +[
+  "claude-sonnet-5",
+  "claude-haiku-4-5"
+]

AddedSep 16, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), it discloses the consent requirement, that omitted fields stay unchanged, the exact semantics of autoMarkMessagesRead (false disables Meta read receipts and coupled typing while AI replies continue, no guarantee of linked-client notifications), and that saving affects future turns without sending a message. This is rich behavioral context that the structured fields do not carry.

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 action and its confirmation precondition are front-loaded, and nearly every sentence carries operational content. It is somewhat redundant, stating omission-preserves-value both in the autoMarkMessagesRead clause and again as "Omitted fields stay unchanged," and it packs multiple instructions into very long sentences.

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 a 5-required-parameter mutation tool with a nested updates object and an output schema, the description covers the safety-critical gaps an agent needs: consent, conflict/retry protocol, idempotency, omission semantics, and read-back-after-success. Nothing essential is 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 description coverage is only 40% (agentId, updates, expectedRevision lack schema descriptions), so the description must compensate. It does add value: idempotencyKey must be reused on retry, expectedRevision drives REVISION_CONFLICT handling, updates preserves omitted fields, and group IDs must be resolved via list_contact_groups. Reasonably strong compensation, though the nested update fields are left to 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?

The description opens with a specific verb+resource ("Update the exact WhatsApp agent") and immediately scopes the operation to a read-confirm-update workflow. An agent can tell this apart from get_whatsapp_agent, list_whatsapp_agents, and update_outbound_assistant without opening the schema.

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?

It gives clear preconditions (read the agent first, confirm account/agent/changes, fresh whatsapp_agents:write consent) and routes group-ID resolution to list_contact_groups. It also prescribes retry/recovery procedure (reuse idempotencyKey/updates/expectedRevision; on REVISION_CONFLICT read and propose again). It does not explicitly name when NOT to use this versus the other update_* siblings, so it stops short of the top tier.

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

All ErzyCall 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?