MCP server 实例审计与孤儿清理

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

No annotations exist, so the description carries the full behavioral burden, and it delivers: read-only by default, termination only with confirm:true plus secondary identity verification, anti-race minAgeSec behavior, and a hard guarantee never to kill client-held instances across tasks. This is a model disclosure of a danger profile for a process-killing tool.

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?

Three dense sentences with the audit scope front-loaded, then orphan criteria, then the guarded destructive path and the safety guarantee. Every sentence earns its place; no filler.

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 tool with no annotations and no output schema, it thoroughly covers the safety-relevant contract: what is audited, what qualifies as an orphan, when termination happens, and when it never will. Minor gaps: the audit's return format is not described and the 'secondary identity verification' mechanism is left unexplained, but neither blocks safe invocation.

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 description coverage is 100% and each of the three params (pids whitelist, confirm gate, minAgeSec race guard) is already well documented in the schema. The description reinforces the confirm default and the orphan criterion that pids depends on, but adds little meaning beyond the schema — baseline 3 applies.

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 names a specific verb and resource — auditing local pango-mcp stdio servers (PID, parent process, age, private memory) and conditionally cleaning orphans. The orphan_candidate criterion is precisely defined (parent gone or parent PID reused), and none of the 45 FPGA-focused siblings perform process or orphan management, so the tool is unambiguous.

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?

Clearly states when the destructive path applies — only orphan_candidates with confirm:true after secondary identity verification — and when it does not (instances still held by clients are never force-killed). It doesn't name an alternative tool because no sibling performs this function, but it gives strong contextual guidance on the read-only default versus cleanup mode.

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