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

The description discloses important behavioral nuances not visible in annotations (which are absent): it explains the meaning of 'active: true' as the default target for other tools when pageId is omitted, clarifies that 'visible' is a WebView-only hint and null for ordinary browser tabs (with tested evidence), and warns that stale tabs accumulate across sessions. These are non-obvious behavioral traits that materially affect how the agent should use the output.

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 highly efficient: every sentence carries meaningful information, covering purpose, output format, key field semantics, usage caveats, and cleanup recommendation in just a few lines. It is front-loaded with the core function and then provides critical details without redundancy or 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?

Given the tool's moderate complexity, the absence of annotations, and the absence of an output schema, the description is exceptionally complete. It explains the return fields, the ordering (newest-active first), the semantic meaning of 'active' and 'visible', the default resolution behavior of sibling tools, and the recommended follow-up action for stale tabs. This is more than sufficient for an agent to use the tool correctly.

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% with both parameters (udid and socket) documented in the schema. The description does not add much beyond the schema for these parameters; the richness of the description is focused on output semantics and usage guidance instead. Since the schema already covers parameter meaning, a baseline of 3 is appropriate.

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 lists debuggable pages/targets on a device and specifies the exact fields returned (id, type, title, url, active, visible). It immediately distinguishes itself from sibling tools by using the specific verb 'list' and the resource 'pages/targets', and further differentiates from related tools like android_devtools_close_page and ios_safari_list_pages.

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 provides explicit practical usage guidance: it explains when you do NOT need to use this tool (acting on the current tab, omit pageId) and when you DO need it (acting on a different tab). It also directs handling of stale tabs by referencing android_devtools_close_page as the cleanup tool. This goes beyond basic context and includes specific exclusions and alternatives.

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