mc_auto

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

No annotations exist, so the description carries the full burden and does so richly: rate limit (120/hour), adaptive backoff (doubling delay up to 30 min, reset on activity), wake timings (5s idle, 45s nudge), threat detection rules (22-block ranged mobs only if line-of-sight, drowning wake triggers), and persistence to `.mcp-mc-agent/auto.json`. It also discloses the safety envelope (no tearing down others' builds, no touching chests, no wandering far), which is exactly the mutation-risk context annotations would normally supply.

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?

The content largely earns its place, but it is a dense wall of bolded Chinese text with heavy emoji use, and the critical action list is buried after two long conceptual paragraphs. The operational essence (what actions exist and what they do) should be front-loaded instead of arriving near the end.

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 complex, zero-annotation, no-output-schema autonomy controller, the description covers actions, defaults, persistence, rate limits, safety boundaries and escalation to the AI. The remaining gap is that `action:"status"` output content is never described, so the agent does not know what the status view returns.

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 the baseline is 3, but the description goes further by attaching behavioral consequences to each `action` value and by naming concrete `patch` keys (`standing`, `idleWakeSec`, `idleWake`, `avoid`) that the schema cannot document because `patch` is `additionalProperties: true` with no listed properties. It stops short of enumerating the full config key set, so it is strong rather than exhaustive.

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?

Opens by naming the resource ("自主行为层") and immediately states the zero-argument default ("不传参数 = 看状态"), then enumerates its two subsystems (reflex layer / idle decision layer) with concrete duties. It differentiates itself from siblings by explicitly noting that mc_say is only for asking about Master's chests/buildings and that `avoid` is a separate switch. It is not a clean verb+resource phrase, but an agent can tell what this tool owns.

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?

Provides an explicit action roster with per-action meaning (status / off / on / stay / follow / wake / set) and calls out the trap that `off` is NOT a full stop, naming the exact `set {"idleWake":false}` and `set {"avoid":false}` needed for full silence. It also states the standing instruction ("Master 在对话里改了主意 → 立刻用 set 把 standing 写成他那句新的") so the agent knows when to invoke `set` versus leaving defaults alone.

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