rms_from_line_free

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

With no annotations, the description carries the burden well: it discloses both output statistics computed, the inclusive indexing convention, the velocity ordering of cube channels, and the bias consequence of the default. The notable omission is that it never states that exactly one of spectrum or fits_path must be supplied, nor the units of the returned rms.

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?

Roughly four sentences, front-loaded with what is computed, then the parameter convention, then the caveat. Every sentence carries technical content; the parentheticals are informative rather than filler, though the density makes it a slightly heavy read.

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?

There is no output schema and no annotations, so the description must do everything. It does describe the return statistics, which is a genuine strength, but leaves out the spectrum/fits_path exclusivity rule and the role of rest_freq_ghz — for a tool with 4 parameters and 0 required, those are the two things an agent most needs.

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 coverage is 0%, so the description must compensate. It fully documents line_free_channels (nested [[start, end]] pairs, inclusive, velocity-ordered, default behaviour) and implies the cube-vs-spectrum split maps to fits_path vs spectrum, but rest_freq_ghz is never mentioned at all — a real gap when the schema is silent.

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 — measuring rms noise from line-free channels of a FITS cube or 1D spectrum — and further pins down the output forms (per-channel and median, robust MAD and plain std). No sibling tool in the list computes noise/rms, so the definition is unambiguous against the 20-tool set.

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 selection guidance for line_free_channels: omit it and all channels are used, with the explicit warning that this biases high if the line is extended. It also adds a domain constraint for PB-corrected cubes (measure before correction or in the field centre). No alternative sibling tool is named, so it stops short of a 5.

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