Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Mirrored from https://github.com/Camo67/composio.git
Synced Nov 21, 08:30 UTC
docs: explain that one execution can return several elicitations
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Mukund committed
Oct 15, 2026 at 18:05 UTC
7100716d5ad199894cf9049ed00259144ef36b93
1 file changed
+2
-2
docs/content/docs/approvals.mdx
+2
-2
@@ -78,7 +78,7 @@ const session = await composio.create('user_123', {
78
</Tab>
79
</Tabs>
80
81
-Tools that need approval stay visible to the agent. In `COMPOSIO_MULTI_EXECUTE_TOOL`, each call that needs approval gets its own question.
81
+Tools that need approval stay visible to the agent, which can find and call them as usual.
82
83
## Asking the user
84
@@ -121,7 +121,7 @@ try {
121
</Tab>
122
</Tabs>
123
124
-`input_requests` holds the questions, keyed by ID. Each one is an [MCP elicitation](https://modelcontextprotocol.io/specification/2026-07-28/client/elicitation):
124
+`input_requests` holds the [MCP elicitations](https://modelcontextprotocol.io/specification/2026-07-28/client/elicitation) for the user, keyed by ID. One tool execution can return several of them, for example when the agent runs several tools at once with `COMPOSIO_MULTI_EXECUTE_TOOL`. Answer all of them when you send the call again:
125
126
```json
127
{