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

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), and the description adds real value beyond them: it defines the null convention for unreported android_api/webview_version and clarifies that a screen's category refers to the device running the app, not panel technology. The unreachability rule for unlisted displays is exactly the kind of constraint an agent cannot get from annotations.

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 the core action, and both sentences carry substantive information. The second sentence is dense and slightly convoluted ('not its panel technology or the display the person has in mind'), but it resolves a real ambiguity about the meaning of 'screen' rather than padding.

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?

An output schema exists, so most of the field-level enumeration (route, support, tools, security modes, runtime APIs, versions) is redundant with structured data. Meanwhile the single input parameter is left unexplained, so an agent can call it but cannot call it precisely — adequate, not complete.

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 0% and there is a single parameter, include_offline (default true), which the description never mentions — the reader cannot tell that offline screens can be filtered out. The phrase 'online/current-view status' hints at online state but does not explain the toggle, so the description fails to compensate for the undocumented parameter.

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?

Opens with a specific verb and resource: 'Lists the caller's authorized screens', then scopes what each entry contains (online/current-view status, route, support, reported android_api/webview_version). This is far from tautological, but it never names or contrasts a sibling (e.g. device_get_status, pages_list), so the agent must infer the boundary between listing screens and getting one screen's status.

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?

Usage is implied rather than stated: you call it to enumerate the caller's screens. The closing rule that a display absent from the list 'is not one of the caller's screens, so no page reaches it' is genuinely useful behavioral guidance for an agent deciding whether to attempt routing, but there is no explicit when-to-use, when-not, or named alternative.

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