get_reference_state

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

With no annotations present, the description carries the full burden and does this thoroughly: it explicitly states the operation is read-only and never changes the display, discloses the six-queries-per-slot cost, and explains the global label_display behavior and the inability to detect stored waveforms.

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?

Every sentence adds meaningful information: purpose, parameter effect, output shape, global-label caveat, limitation, safety, and cost. The structure is front-loaded with the definition and branches into details, with no redundant or filler text.

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?

Because no output schema is provided, the description needs to explain return shapes and caveats, and it does. It covers both response forms, the field set, the global label switch behavior, the unqueryable stored-waveform status, and the query cost — enough for an agent to call and interpret results 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?

The input schema only defines 'ref' as an optional integer/null with zero description coverage. The description compensates fully by specifying the valid range (1-10), the flat return with ref, the keyed channels structure without ref, and the string-keyed slot numbers.

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 opens with a specific verb and resource ('Return the reference waveform settings') and enumerates the returned fields. This clearly distinguishes it from sibling getters like get_channel and get_state, which target different subsystems.

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?

It clearly explains the two invocation modes (ref given vs omitted) and the resulting response shape, and notes that the tool cannot be used to check whether a slot holds a stored waveform. It does not name an alternative sibling, but there is no ambiguous overlap for reference-state queries, so the context is sufficient.

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