Invoke a tool on a server this host has not loaded

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

Beyond the destructiveHint annotation, the description discloses connection lifecycle (opened/closed per call), policy enforcement, error categorization, self-correction on unknown tool names, and audit logging with argument names only. This is a rich behavioral contract.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence carries distinct value: core function, lifecycle, policy, error handling, self-correction, audit. It is well-structured and front-loaded with the main purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's dynamic nature (invokes arbitrary tools) and 7 params with no output schema, the description covers key aspects: addressability, policy, error handling, and audit. The return shape is undefined but that's expected; the description could add expected result structure, but it's acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 7 parameters have schema descriptions, so the baseline is 3. The description adds context on server resolution (MCP root/profile) and args passthrough, but doesn't go into depth per parameter. It's sufficient given the schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States exactly what it does: runs one tool of an unloaded backend MCP server and returns the result. The verb+resource is specific and distinguishes it from all sibling tools, which manage or describe but do not invoke.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes clear this is for invoking tools on servers not part of the current session. It notes constraints (discoverable from MCP root or profile, policy can deny) but doesn't explicitly contrast with in-session invocation. However, the title and content imply when to use it.

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