uad_safe_state

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

With no annotations, the description carries full weight. It discloses the key behavior (muting all monitor outputs, turning off talkback) and, importantly, that it 'takes no arguments and needs no confirmation,' which sets expectations about immediacy and irreversibility. It doesn't mention return values or side effects beyond the audio state, but the stated behavior is unambiguous for a panic action.

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 short sentences: the first defines the action, the second gives usage context, the third names an alternative for a different use case. Every sentence is purposeful and information-dense. The 'Panic button' label front-loads the intent.

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?

The tool is simple (no parameters, no nested objects). The description covers purpose, usage, and exclusions. It also provides a fallback alternative. Given the low complexity and presence of an output schema, no further detail is required.

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?

There are zero parameters, so the description's assertion 'takes no arguments' adds value by confirming the schema's empty properties. Per the rubric, 0 params yields a baseline 4, and this description explicitly reinforces that.

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 'Panic button' and immediately defines the action: 'mute every monitor output and turn talkback off.' This is a specific verb-resource-scope statement that clearly differentiates it from siblings like uad_set_channels and uad_talkback.

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?

Provides explicit when-to-use ('there is feedback, a runaway level, or anything unexpectedly loud'), sequencing advice ('Call it first and diagnose afterwards'), and a clear when-not-to-use with an alternative tool ('normal muting of a single channel - use uad_set_channels').

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