mc_stop

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

No annotations are provided, so the description carries the full burden, and it does: it discloses the graceful-then-forceful shutdown sequence, what gets destroyed (all session background tasks, watchdog), and the key side-effect boundary (does not abort the caller's own turn; server cannot stop the client turn; no force-stop exists). That is exactly the behavioural context an agent needs before invoking a destructive session-level operation.

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 core action is front-loaded in the first sentence, with warnings after it in priority order. It is somewhat verbose and uses a parenthetical aside about stoppedLLM that adds little, but nearly every sentence carries a distinct behavioural fact.

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 one-parameter, no-output-schema, no-annotation tool, the description covers what it does, when to use it, what it destroys and what it cannot do. It does not state failure behaviour (e.g. what happens if the game does not quit gracefully) or confirm whether the session remains usable afterwards, which is a minor remaining gap.

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?

One optional parameter (reason) with 100% schema description coverage, so the schema already explains its meaning ('reason, written to log'). The description adds nothing about the parameter, and the baseline 3 applies when the schema does all the work.

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?

Specific verb+resource (stop this session's Minecraft) plus a concrete two-phase behavior: graceful game quit, then clearing all session background tasks including the watchdog. It never references the sibling mc_disconnect, which is the most obvious semantic neighbour, so an agent cannot fully disambiguate from the text alone.

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 an explicit use case ("I don't want to play anymore, log off") and an explicit non-use case with the alternative action ("to stop your own running action, just don't call tools"). It also states there is no force-stop path, which closes off a tempting misuse. Missing only a comparison against mc_disconnect/mc_task for the overlapping 'tear down state' scenario.

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