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

Annotations already declare destructiveHint=true, but the description adds concrete consequences beyond them: ~40s unreachability, stream drop, MCP session teardown, and loss of in-progress work. It also surfaces the confirm=true requirement and that there is no default, which is meaningful behavioral context for a destructive call.

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-loaded with purpose, then consequences, then routing guidance, then the counterpart. Five sentences, each carrying distinct information; no filler.

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 destructive, no-output tool, the description covers purpose, irreversibility, timing, required confirmation, when-not to use it, the preferred alternative, and the iOS sibling. Nothing an agent needs to call this 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 100% and the schema already documents both udid and confirm (including const=true and its acknowledgment meaning). The description's 'Requires confirm=true — there is no default' largely restates that, adding only the no-default nuance. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Reboot an Android device') and explicitly names the sibling alternatives device_release and ios_reboot. An agent can distinguish this from every other device_* tool without opening a 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-not guidance ('Do NOT reach for this to recover from a flaky tool call; try device_release first') and an explicit when ('Reboot only when the device itself is wedged and a human has asked for it'). The alternative and the condition that selects it are both spelled out.

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