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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds real behavioral context beyond them: the session and running apps survive, and re-entry is gated on owner credentials. It does not say whether an already-locked screen errors or what the response reports, but the credential gate is the meaningful disclosure.

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, no waste, with the primary behavior front-loaded and the credential consequence second. Nothing is repeated from the schema or annotations.

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?

Output schema exists and annotations cover safety, so the description need not explain returns. It covers the effect on the machine and the unlock prerequisite. A note about interaction with power_sleep or the delayed-execution case would close the remaining gap, but nothing required to call it correctly 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 description coverage is 100%, so both 'device' and 'delay_seconds' (including the 90-second cap and the reason for it) are already fully documented. The description adds nothing about either parameter, so the baseline 3 applies.

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 target ('lock the paired computer screen') and clarifies the scope by contrasting it with harsher power actions: the OS and active applications keep running. An agent can distinguish it from power_sleep/power_shutdown without opening the schema, though it never names those siblings explicitly.

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?

The opening 'Use this to lock...' plus the note that unlocking requires device owner credentials gives implied usage and a prerequisite. There is no explicit when-not guidance or named alternative (sleep/shutdown/restart), leaving the agent to infer the selection rule.

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