Sheet: Extract Data

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

With only destructiveHint=false in annotations, the description carries real behavioral weight: it discloses three distinct failure modes, the capability flag 'xlsx_write', and the fact that nothing is written on an empty drawing. This goes well beyond the annotations. It does not describe overwrite behavior for an existing path, which slightly limits it.

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 compact paragraphs with the identifying comparison front-loaded and a labeled 'Refusals:' block that earns its space by covering edge cases. Slightly dense dash-heavy prose but no wasted sentences.

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?

With an output schema present, return values need not be explained, and the description covers the operational hazards an agent needs (format support, dependency, empty input). It leaves the file-overwrite/pre-existing-file case unaddressed, a minor gap for a file-writing tool.

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 already 80% and documents fmt, path, layer, columns, and group_by with enums and defaults. The description reinforces the fmt/openpyxl constraint but adds no syntax or format detail for path extensions, layer filtering, or grouping beyond what the schema states, so the baseline 3 applies.

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?

It names the resource ('the same rows bom_extract returns') and the distinct action ('written to a file'), which cleanly separates it from its closest sibling bom_extract without requiring the schema. An agent can tell immediately that this is the export counterpart to the extract tool.

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 refusal list effectively states when the tool will not work (unsupported format, empty drawing, xlsx without openpyxl) and points to the CSV route as the always-available alternative. It implies the use case implicitly via the bom_extract comparison but never says explicitly 'use this instead of bom_extract when you need a file', so it falls short of a full 5.

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