mcp_tool_call

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: exactly one JSON-RPC call per invocation, execution inside a session on the hosted server, and a {status, response} return where errors surface as JSON-RPC results rather than exceptions. It omits authentication requirements for the hosted server, whether the session persists across calls, and any rate or size limits.

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?

Two tight sentences, front-loaded with the action and endpoint, followed by the wire protocol and return shape. The JSON-RPC 2.0 phrasing is slightly mechanical but not wasteful.

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?

The return shape is explained inline, which compensates for the absent output schema, and both parameters are covered. However, for a generic-proxy tool with no annotations, the description leaves out how an agent discovers valid hosted tool names and what credentials or session setup the hosted server requires — both essential to invoking it correctly.

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?

Schema coverage is 100%, so both parameters are already documented, establishing a baseline of 3. The description confirms that arguments is an uninterpreted pass-through coupled with name, which is useful, but it does not tell the agent where to find the hosted tool's expected argument schema, which is the real semantic gap for a generic proxy.

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 a specific verb and mechanism: it invokes one tool on the hosted MCP server at mcp.servonaut.dev via a single JSON-RPC tools/call. The resource and transport are unambiguous, but nothing distinguishes it from its many concrete siblings (aws_call, api_request, run_command) or says why an agent would pick this generic proxy instead.

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?

No guidance on when to use this versus the dozens of concrete sibling tools, or versus api_request and aws_call, which appear to serve similar generic-proxy roles. No prerequisites (credentials, session state) or exclusions are stated, leaving the agent to infer the selection rule.

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