get_waveform

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

With no annotations, the description carries the full burden and does so well: it discloses that sample arrays are never inlined (context protection), that RAW mode stops the instrument first, and that CSV is refused above the point threshold unless forced. It stops short of naming exact permission/auth needs, but the behavioral profile is substantially richer than the schema alone.

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?

Front-loaded with the core action and the critical output caveat, then a compact per-parameter reference broken into short labelled lines. Dense but each line earns its place; slightly long, though justified by 11 parameters.

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 an 11-parameter tool with zero schema descriptions and no annotations, the description supplies the operational context an agent needs to call it correctly, and even explains return semantics despite an output schema existing. Minor gaps (filename handling, explicit exclusions vs. siblings) keep it from the top score.

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 compensate and largely does: it explains source, mode, fmt, start/stop, points (including the subtlety that providing points skips the RAW start/stop default), save_format, force_csv, and max_csv_points. Only filename and stop_instrument_first are not directly addressed.

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+resource (acquire waveform data and save to a local file) and clarifies the output shape (metadata + file path, no inlined arrays). It distinguishes itself implicitly from on-instrument siblings (save_waveform_on_instrument) by emphasizing the local file, but never names an alternative, so differentiation is inferential rather than explicit.

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?

Gives real conditional guidance (RAW for full memory and stops the instrument first; npy recommended for RAW ≥ 1M points; CSV refused above max_csv_points). However it never names a sibling such as export_waveform_csv, get_waveform_preamble, or get_math_waveform to route the agent, so the when-to-use-this-vs-that question is left to inference.

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