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

Annotations only say readOnlyHint=false and destructiveHint=false, so the description must carry the behavioral load and it does: it describes the post-condition ('Returns to the same screen as before the lock'), a named failure mode (not_locked), and a side effect (logged in device_log as simulated). What is missing is whether unlock can fail for other reasons or what the success response contains.

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?

Four short sentences, front-loaded with the physical action, then the post-condition, the error, and the logging note. Every sentence contributes distinct information with no repetition of the name 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?

For a one-parameter, non-destructive device action with no output schema, the description covers action, resulting state, error condition, and observability. It is close to complete, though it leaves open what other failure modes exist beyond not_locked.

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% and the single session parameter is already documented as 'Session from open_app', so the schema does the work here. The description adds no session-specific meaning such as whether a stale or ended session is rejected. 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 concrete verb and target: 'Swipe up on the lock screen' names the exact gesture and state being changed, so an agent can distinguish it from siblings like lock, press_home, or screen. It does not explicitly name the complementary sibling (lock), which keeps it just short of a 5.

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 description supplies an implicit precondition by stating it 'fails with not_locked if the phone is not locked,' which tells the agent exactly when this tool is applicable and when it will error. It does not discuss recovery paths or alternatives after such a failure, so there is no explicit when-not guidance.

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