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

The description adds useful context beyond the schema by noting the return is a 'structured list of active notifications (app, title, text)', indicating the read-only nature (mentioning 'Read'). However, no annotations exist and the description doesn't disclose potential limitations like notification access permissions, OS version restrictions, or timeout behavior. Reading is non-destructive by implication but not explicitly affirmed.

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?

The description is a single concise sentence that efficiently conveys the purpose and return structure. There's no wasted verbiage. Could arguably add a usage qualifier but earns high marks for efficiency.

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 simple read tool with one well-documented parameter and no output schema, the description is serviceable. It explains the return structure clearly ('structured list of active notifications (app, title, text)'), compensating for the lack of an output schema. However, it lacks mention of potential edge cases like empty notifications, permission issues, or how it compares to device_shell or other system inspection tools.

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?

The single parameter 'udid' is fully documented in the schema (100% coverage) as 'Device serial number (UDID)'. The description doesn't add anything beyond what the schema provides—no format hints or context about required device state. Baseline 3 is appropriate given full schema coverage.

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?

The description clearly states the tool's function: 'Read current notifications on an Android device' with a specific verb (Read) and resource (notifications). It also describes the return structure ('structured list of active notifications (app, title, text)'). It doesn't strongly distinguish from siblings, but among many android/device tools it's reasonably unique in purpose.

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?

No guidance on when to use this tool vs alternatives. It doesn't mention prerequisites (e.g., needing a device session or notification permission), whether it requires a connected/live device, or note that some notifications may not be accessible. No exclusions or alternative tool references.

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