Low Risk

describe_object

Describe the structure of a Snowflake object

Part of the Snowflake MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

@snowflake-labs-mcp Read Risk 2/5

AI agents call describe_object to retrieve information from Snowflake without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though describe_object only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

snowflake.yaml
tools:
  describe_object:
    rules:
      - action: allow

See the full Snowflake policy for all 10 tools.

Tool Name describe_object
Category Read
Risk Level Low

View all 10 tools →

Agents calling read-class tools like describe_object have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the describe_object tool do? +

Describe the structure of a Snowflake object. It is categorised as a Read tool in the Snowflake MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on describe_object? +

Add a rule in your Intercept YAML policy under the tools section for describe_object. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Snowflake MCP server.

What risk level is describe_object? +

describe_object is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit describe_object? +

Yes. Add a rate_limit block to the describe_object rule in your Intercept 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.

How do I block describe_object completely? +

Set action: deny in the Intercept policy for describe_object. 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.

What MCP server provides describe_object? +

describe_object is provided by the Snowflake MCP server (@snowflake-labs-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Snowflake

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.