list-devices

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

With no annotations provided, the description bears the full burden of behavioral disclosure, and it excels. It extensively details behaviors beyond the basic listing: state semantics ('connected', 'paired', 'running', 'stopped'), ordering (booted/ready first), silent omission of unavailable platforms, headless behavior for additional device sets, discovery mechanisms (CDP ports, env var), and platform-specific nuances (physical phones detected via adb, TV targets are focus-driven). It also explains return structure and how to interpret entries. This is exemplary transparency for a tool with no 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?

The description is notably long but densely packed with critical information; every sentence adds unique value. It is front-loaded with the core purpose and usage, then systematically details each device type. While it could be criticized for length, it avoids redundancy and organizes content logically (general, then per-platform). It is somewhat verbose, but the complexity of the tool justifies the length. The structure is effective for parsing, with clear topic shifts.

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 high complexity—multiple device types, special cases, configuration dependencies—the description is remarkably complete. It covers return format, state semantics, ordering, platform-specific quirks, configuration (additionalDeviceSets, Chromium ports), and even failure modes (silent omission). With no output schema and no annotations, the description supplies all necessary information for correct invocation and interpretation. It leaves nothing essential unexplained.

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 tool has zero parameters, and the schema coverage is 100% (empty schema). There are no parameters to document, so the description does not need to explain parameters. However, the description extensively explains the output structure (devices and avds, platform discriminators, kind, state), which is arguably more valuable than parameter semantics. Since there are no parameters, a score of 4 is appropriate as it fully compensates for the absence of parameter details by richly documenting the return semantics.

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 begins with a clear, specific statement of what the tool does: lists multiple device categories (iOS simulators, Android emulators, physical Android devices, Chromium apps, Vega devices) 'in one place'. It distinguishes itself from sibling tools by emphasizing its role as a discovery and enumeration tool, separate from booting (boot-device) or interacting with devices. The purpose is unequivocal and concrete.

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 when-to-use guidance: 'Use at the start of a session to pick a target id'. It also gives practical usage instructions for different device types, such as which ID field to use for each platform, and how to handle special cases (e.g., for TV targets use tv-remote instead of gesture tools). It addresses alternatives indirectly by referencing sibling tools like boot-device and fold, and explains when they are relevant. The guidance is thorough and actionable.

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