Return to the MiSTer menu

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

Annotations declare destructiveHint=true; the description goes further by naming exactly what is destroyed (unsaved in-game progress) and by mandating user confirmation before the call. It also adds host-resolution behavior not covered by annotations.

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?

Two sentences, front-loaded with the action, followed by the risk warning and the default-targeting rule. Nothing is padded or repeated from the schema.

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 single-optional-param destructive action with an output schema and full annotations, the description covers the action, its consequence, the required user confirmation, and host defaults. Nothing an agent needs in order to call it safely is missing.

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 already 100%, so baseline is 3; the description adds genuine meaning by explaining the fallback semantics of omitting host ('acts on the one MiSTer that's running something'), which the schema itself only hints at.

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 ('end whatever is running') and destination ('back to the MiSTer menu'), which cleanly distinguishes it from write-oriented siblings like launch or run_update. The scope ('whatever is running') 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?

Gives a clear precondition for calling: confirm with the user first because progress is lost. It also explains default targeting when host is omitted. It does not name an alternative tool, but there is no obvious competing sibling for this action.

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