Server health (read-only)

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that: the scope is this server process rather than the device, it tracks live child processes, and it includes an Android-specific risk assessment. It stops short of saying anything about cost, frequency, or what an unhealthy result looks like, but the scope and content disclosure is solid.

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?

Front-loaded with the scope ("Read-only self-diagnostics for this MCP server process"), then the returned signals, then the usage boundary against `device_status`. The field enumeration is dense but each item is a distinct diagnostic the caller may need, so nothing reads as padding.

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?

With no output schema and no parameters, the description carries the full burden of telling the agent what comes back, and it does: it names the four top-level return keys {server, children, memory, phantom_process} and the highlights of each. An agent has everything it needs to decide to call it and to interpret the response shape.

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 takes zero parameters, so the baseline is 4. The description correctly implies no configuration is needed by framing the call as pure self-diagnostics, and it supplies no misleading parameter hints.

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 resource ("read-only self-diagnostics for this MCP server process") and enumerates exactly what it reports: pid/ppid, uptime, counters, children, RSS, Phantom Process Killer risk. It explicitly distinguishes itself from the sibling `device_status`, so an agent can route correctly without opening either schema.

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?

Gives three concrete triggers (verify the server is alive, debug client-side disconnects, check for accumulating orphaned children on Android) and an explicit exclusion with a named alternative: "Not for the device itself: use `device_status` for battery, storage, arch and memory."

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