iyke_mcp_restart

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

With no annotations, the description carries full burden. It discloses scope (restarts all entries per pkg) and failure mode (404). However, it does not mention side effects, permissions needed, or idempotency. Some aspects are implied but not explicit.

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 sentences, each adding value. First sentence announces action, second clarifies scope, third provides usage context and failure condition. No fluff, well front-loaded with action.

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 no annotations or output schema, the description covers purpose, scope, and failure condition. It lacks information on expected return value or success confirmation. For a restart tool, agents would benefit from knowing if restart succeeded or any async behavior.

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?

Only one parameter, pkg_id, with 0% schema description coverage. The description mentions 'by pkg id' confirming parameter meaning. However, it does not explain format or provide guidance on obtaining pkg_id, which would help agent.

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?

Description clearly states verb 'Restart' and resource 'supervised MCP server by pkg id'. It distinguishes by specifying that it restarts every long-lived MCP entry per pkg, not per server name, and contrasts with per-call MCPs which cannot be restarted.

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?

Explicitly states when to use: 'Useful when a child has wedged.' Also explains when it fails (404 for non-supervised pkgs) and why per-call MCPs are not restarted. Does not suggest alternative tools for non-supervised pkgs, but context is clear.

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