Returns the full parameter schema (name, placement, required, JSON Schema) for a tool discovered via search-tools. Call this before execute-tool so you know what parameters to pass and what enum values are valid.
AI agents call get-tool-schema to retrieve information from Ms 365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves schema metadata about available tools. It does not modify, delete, or execute any operations—it merely provides introspective information needed before execution. The low severity reflects that exposing tool schemas carries minimal direct risk, though an agent could use this information to inform subsequent calls to execute-tool or other write/execute operations.
From the tool's definition Tool description states it 'Returns the full parameter schema' for tools—a retrieval operation with no side effects. The verb 'Returns' and the purpose of querying metadata about other tools indicate a read-only information lookup.
Attacks that exploit this kind of access
Returns the full parameter schema (name, placement, required, JSON Schema) for a tool discovered via search-tools. Call this before execute-tool so you know what parameters to pass and what enum values are valid. It is categorised as a Read tool in the Ms 365 MCP Server, which means it retrieves data without modifying state.
Register the Ms 365 MCP server in PolicyLayer and add a rule for get-tool-schema: 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 Ms 365. Nothing to install.
get-tool-schema is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get-tool-schema 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 get-tool-schema. 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.
get-tool-schema is provided by the Ms 365 MCP server (@softeria/ms-365-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →