select_device

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

With no annotations, the description carries the full load and does disclose key state behavior: the choice is session-scoped and shared across every agent hitting the server, which is a non-obvious side effect. It does not say what happens on an unknown device or an ambiguous name substring, so error behavior remains undisclosed.

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?

Three tight sentences, front-loaded with what the tool does, then the multi-agent caveat, then the clearing instruction. No filler and nothing important buried at the end.

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 single-optional-parameter tool with no output schema, the description covers effect, lifetime, sharing scope, and reset. The only real gap is failure semantics for a nonexistent or ambiguous device identifier, a minor omission given the tool's simplicity.

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 100%, so the parameter is already documented as 'Device UDID or name substring; omit to clear'. The description adds genuine meaning beyond the schema by explaining how the stored value is consumed by later calls that omit 'device', which the schema does not convey.

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 (choose) and resource (device) plus the exact effect: it sets the default device for later calls that omit 'device'. That is clearly distinct from siblings like list_devices or install_app, so an agent can identify it without opening the 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?

Explicitly gives when-to-use (set a default for subsequent calls), when-not-to-use (parallel agents on different devices should pass 'device' per-call instead), and how to undo (omit 'device' to clear). All three routing questions an agent could have are answered in the description itself.

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