host_info

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

With no annotations provided, the description carries the full behavioral disclosure burden. It discloses the return value for local launches ('local started') and implies an endpoint for remote cases. It does not detail the exact shape of the remote endpoint beyond 'username@ip', but for a zero-parameter, read-only tool this is sufficient and adds value beyond a bare 'query' phrase.

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 concise sentences, front-loaded with the purpose and followed by the behavioral caveat. No wasted words; every clause adds distinct information.

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?

For a zero-parameter, no-output-schema tool, the description is fully complete: it states what the tool does, specifies the triggering scenario, and describes the two possible return states. Nothing essential is missing.

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?

The tool has zero parameters, so the baseline is 4; the description correctly adds no parameter information since none exist. The schema coverage is 100% because there is nothing to document, and the description's scenario context is the only additional relevant semantic.

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?

The description clearly states a specific action ('Query the MCP host endpoint') and resource ('username@ip'), and distinguishes this tool from the many ssh/serial/adb siblings by focusing on host information for scp construction. It explicitly names the output format (username@ip) and the conditional local-launch behavior.

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 gives a concrete use case: constructing cross-machine file transfers when the MCP runs on Windows and the AI client on Linux. It also provides an exclusion by stating that local launches return 'local started' with no endpoint, implying the tool is not useful in that scenario.

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