list_devices

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the enumerated state values (device, offline, unauthorized) and the operational consequence that only 'device'-state entries accept commands, which is exactly what an agent needs to act on the result.

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?

Two short sentences, zero filler, with the primary purpose front-loaded and the state semantics immediately after. Every clause carries information the agent needs.

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 zero-parameter read tool with full annotation coverage and an output schema, the description supplies enough: what is listed and how to interpret the state field. The only missing piece is an explicit sequencing cue that this call should precede device-scoped actions, which is implied but not stated.

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 takes zero parameters, so there is nothing to disambiguate; the baseline for a no-parameter tool applies. The description does not invent or misdescribe inputs, and the meaningful detail it provides is about output state rather than inputs.

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 specific verb and resource ('List attached Android devices and emulators') plus what is returned ('with their state'), which cleanly separates it from the sibling tools that all act on a single device (tap, install_apk, logcat, etc.). An agent can identify this as the discovery/enumeration tool without opening any schema.

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 clause 'only "device" accepts commands' implicitly tells the agent to check state before invoking action tools, which is useful guidance. However, it never explicitly says to call this tool first to discover device IDs, and it does not name any alternative or state a when-not condition, so the guidance remains inferential.

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