Write a SCAPS input file

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

Annotations declare destructiveHint=true for a file-writing tool, yet the description never mentions that an existing file may be overwritten or that overwrite defaults to false and must be set deliberately. It also says nothing about where files land or whether writes are visible to other tools. Beyond restating 'right format and units', it adds no behavioral context that the annotations do not already carry.

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?

Two short sentences with the core action front-loaded and the supported data types listed after. There is minor waste in the vague phrase 'with the right format and units', which conveys little the schema doesn't.

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 output schema and rich parameter schema relieve the description of return-value and per-parameter explanation. However, for a 19-parameter destructive write tool, the description is thin on the overwrite/safety story and on how kind selects which optional parameters matter.

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 95%, including per-kind semantics for x, y, quantity, and x_unit, so the schema does most of the work. The description adds only the general 'format and units' framing, with no extra cross-parameter guidance (e.g., matching quantity to kind or units to x_unit). Baseline 3 is appropriate.

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 states a specific verb and resource: write numeric data as a SCAPS input file, including that formatting and units are handled. It enumerates the data families (absorption, spectra, generation, filters, grading, measurement), which maps cleanly onto the kind enum. It does not distinguish itself from scaps_import_file, which could plausibly handle similar data.

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 second sentence gives a positive usage scope that matches the six kind values, so an agent can tell roughly when the tool applies. There is no guidance on when not to use it, no mention of scaps_import_file as the alternative for existing files, and no note on when overwrite should be set.

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