configure_afg

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 so thoroughly. It reveals that the output state is never touched, that out-of-range values are silently clamped with no error reported, that writing frequency while waveform is dc/noise is rejected, and that duty and symmetry settings are stored independently of the current waveform. This goes well beyond the input schema and gives an agent realistic expectations about side effects and failure modes.

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?

Although the description is long, it is dense and every sentence earns its place given the zero coverage in the schema and nine parameters. The most important behavioral fact (never toggles output) is front-loaded right after the core purpose, and parameter details are grouped logically. No filler or repetition is present.

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 description is comprehensive for a complex configuration tool with no annotations and no output schema. It covers the output-state relationship, parameter meanings, units, valid values, clamping behavior, error rejection, and read-back guidance via 'compare applied (the read-back value) against requested.' An agent has enough context to invoke the tool correctly and interpret results.

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 description coverage is 0%, so the description must explain all parameters, and it does. It lists valid waveform strings, defines amplitude_vpp as peak-to-peak volts (not peak or RMS), specifies units and ranges for phase, duty, and symmetry, and explains the meaning of impedance. It also adds important caveats about parameter interactions, such as rejected frequency writes for dc/noise waveforms.

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-resource pair ('Configure the built-in function generator (AFG)') and immediately clarifies the scope with 'Omitted items are left unchanged.' This clearly distinguishes it from sibling tools like enable_afg, disable_afg, and get_afg_state, which are explicitly named in the description.

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 gives explicit usage context: it does not turn output on/off, and it names the separate confirmation-gated tool enable_afg and disable_afg for that purpose. It also directs the user to get_afg_state for reading the current state, and distinguishes the AFG impedance setting from the oscilloscope input impedance in configure_channel. These are clear when-to-use and when-not-to-use guidelines.

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