dd2_quit

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

No annotations are provided, so the description carries the full load, and it does substantial work: it discloses that this is a hard kill with no clean exit path, and that data loss is avoided only if the save guard is armed. What it does not state is what happens if the guard is not armed, or whether it fails gracefully when the game isn't running.

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 action and its kill semantics are front-loaded in the first clause, ahead of the safety caveat. Two sentences is the right size, though the stacked parentheticals and the unresolved question mark in 'test units only?' add noise an agent must interpret.

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?

An output schema exists, so return values need not be described, and the description still flags that a saves report comes back. For a destructive one-parameter tool with no annotations, it covers the essential risk and prerequisite; only the unarmed-guard failure mode is left unspecified.

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 0%, so the description must compensate, and it does: it gives the exact accepted format 'YYYY-MM-DD HH:MM[:SS]' and explains that the parameter triggers a report of saves written since that time. The trailing 'test units only?' hedges the scope of the parameter rather than clarifying it.

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 and resource: 'Close DD2', immediately qualified as a 'hard kill' because there is no scripted clean exit. That combination tells an agent exactly what the tool does and distinguishes it from dd2_launch. It falls short of 5 only because the trailing 'since' sentence muddies the main action with a secondary reporting behavior.

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 trigger condition, 'as soon as in-game testing ends', which implicitly excludes using it during active testing. It also surfaces a prerequisite by noting that with the save guard armed nothing is lost, pointing an agent at dd2_saveguard before invoking, though the sibling is never named explicitly.

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