power

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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds genuinely new runtime context: two environment gates (WISP_ALLOW_POWER, WISP_ALLOW_DESTRUCTIVE) that must be set, and the clarification that kill is a forced stop. It does not describe post-action state or return behavior, so not a 5.

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, action vocabulary front-loaded, permission constraints after. No filler or repetition of the tool name.

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 two-parameter mutation tool with full schema coverage and annotations carrying the safety profile, the description covers intent, gating, and the destructive variant. What remains unstated — graceful vs. hard stop semantics and the response shape — is minor given there is no output schema.

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% and the enum plus server_id default are fully documented there, so the baseline is 3. The description only echoes 'force-kill' for the kill signal and adds no format or precedence detail beyond the schema.

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?

Names a specific verb ('Change a server power state') and enumerates the exact action set (start, stop, restart, force-kill). No sibling in the list touches power state, and the mention of force-kill separates it from the softer console/command tools such as send_console_command.

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 guard ('Use only when a power action is intended') plus the permission preconditions for the tool and for its destructive variant. It stops short of naming alternatives for non-power interventions, so conditional routing to siblings is left implicit.

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