/ * Adds a new user observation to an existing investigation. * * Prerequisites: * Argument Resolution: Before invoking this tool, you MUST resolve any new resource names mentioned in the user's observation into the specific formats required by the arguments. * * Resource URI Mandate: If the user...
Part of the Gemini Cloud Assist server.
Free to start. No card required.
AI agents use add_observation to create or modify resources in Gemini Cloud Assist. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call add_observation repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Gemini Cloud Assist.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"add_observation": {
"limits": [
{
"counter": "add_observation_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Gemini Cloud Assist policy for all 4 tools.
These attack patterns abuse exactly the kind of access add_observation gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
/ * Adds a new user observation to an existing investigation. * * Prerequisites: * Argument Resolution: Before invoking this tool, you MUST resolve any new resource names mentioned in the user's observation into the specific formats required by the arguments. * * Resource URI Mandate: If the user's 'observation' mentions new resources, the 'relevant_resources' parameter requires a list of full Google Cloud Platform (GCP) resource URIs. If no new resources are mentioned, provide an empty list '[]'. * - Format: Each URI MUST strictly adhere to the format: //<service>.googleapis.com/<resource-path>. * - Validation: The tool will fail if any provided strings are not well-formed URIs in this exact format. * - Resolution: You are responsible for converting any partial, ambiguous, or incomplete resource names into their full URI representation. Utilize available tools like 'gcloud', 'kubectl', or your internal knowledge base to discover the complete and accurate resource URIs. * - GCP Resource URI Reference: https://cloud.google.com/asset-inventory/docs/asset-names * * Example of a correct GCP Resource URI: * - //compute.googleapis.com/projects/my-gcp-project/zones/us-central1-a/instances/my-vm-instance * * Crucial: If you cannot resolve a new resource name into the required format, you MUST seek clarification from the user before proceeding to call this tool. * * Workflow: After adding an observation, you MUST call 'run_investigation' on the new revision to re-analyze with the added context. * * @returns {string} A string summary of the updated investigation, structured with Markdown. * You MUST parse this output to find the 'Revision Path' field. * The final segment of this path is the new 'revision_id' that you must * use for the subsequent 'run_investigation' call. */. It is categorised as a Write tool in the Gemini Cloud Assist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gemini Cloud Assist MCP server in PolicyLayer and add a rule for add_observation: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gemini Cloud Assist. Nothing to install.
add_observation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_observation rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for add_observation. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
add_observation is provided by the Gemini Cloud Assist MCP server (@google-cloud/gemini-cloud-assist-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Gemini Cloud Assist tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.