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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds real behavioral context: the two-tier routing, the shell fallback on error/timeout, the always-shell policy keys, and the crucial constraint that every route is injected with no kernel input path.

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?

Front-loads the core action, then routing rules, then the alternative. Dense but each sentence carries distinct, non-redundant information; the parenthetical key lists run slightly long but earn their place given no enums in 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 2-param mutation tool with no output schema, the description covers routing behavior, fallbacks, exceptions, and the sibling decision, leaving nothing an agent needs to call it correctly 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 coverage is 100% and already documents both params, so the baseline is 3. The description goes slightly further by supplying the numeric equivalents for policy keys (187/82/26) that the schema does not map, adding marginal meaning beyond the enum-less 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?

States a specific verb and resource ('Send a keycode to a device') and explicitly differentiates itself from the sibling device_uhid_key_press by contrasting injected routes against kernel input. An agent can select between them without opening either schema.

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 explicit when-to-use guidance: policy keys (APP_SWITCH/187, MENU/82, POWER/26) always go via shell, other keys try the control channel then fall back, and it names the exact alternative (device_uhid_key_press) plus the condition that selects it (target app filters or ignores injected events).

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