capture_waveform

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

With zero annotations, the description carries the full behavioral burden and delivers exceptionally: CSV file fallback when there are many points with the path returned in data_file, screen decimation with a prescribed way to recover the true sample rate, and the FFT math-trace special case (x_unit 'Hz', sample_interval_s as frequency step, absent effective_sample_rate_sa_per_s). These are exactly the non-obvious behaviors an agent needs to interpret results correctly.

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?

Four paragraphs, each load-bearing: core purpose and unit conversion, channel semantics and prerequisites, output/decimation behavior, then the FFT edge case. The description is front-loaded with the primary purpose and contains no filler or repetition of schema fields.

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 tool with no output schema and no annotations, coverage is strong: return units, data_file path, sample-interval and x-axis semantics, and the FFT frequency-domain exception are all documented. The one vague spot is the normal time-axis case being left as 'the usual shape,' which assumes agent familiarity with the general return structure.

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?

With 0% schema description coverage, the description must compensate, and it does thoroughly for channel, documenting valid values, the two categories of sources, and their differing read semantics. max_points is only indirectly addressed through the 'many points' CSV behavior; its actual role in decimation or data-size limiting is never made explicit.

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 ('Capture waveform data') plus distinctive behavior ('return it converted to volts (V)'), which clearly separates it from capture_screenshot and measure. The channel domain is spelled out exactly ('CH1'-'CH4' or math trace 'MATH1'-'MATH4'), leaving no ambiguity about what this tool produces.

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 prerequisites: math traces must be configured via configure_math and their display turned on before capture. It names a sibling tool (configure_math) and gives actionable context. However, it never explicitly contrasts this tool with related alternatives like measure or analyze_waveform for the common CH1-CH4 case, so it stops short of full when/when-not guidance.

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