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

Beyond the annotations (idempotent, non-read-only, non-destructive), the description discloses that no FO credentials are needed, that autoGeneratedFields are stripped from the output 'so FO generates them', and that base64 upload is limited to small files. It also exposes the CSV-vs-JSON output differentiation and the listSheetsOnly diagnostic mode. No statement contradicts the annotations, and the idempotentHint=true aligns with the offline pure-transform behavior.

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?

The description is front-loaded with the core purpose and the key differentiator (offline transform, no credentials), and nearly every sentence carries load-bearing information with zero fluff. However, the mapping spec details are crammed into a single dense sentence with mixed bracket notation, and breaking the content into short bullets or lines would improve parseability without adding bulk.

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 8-parameter tool with no output schema, the description covers input source constraints ('one of', 'small files only'), the mapping spec shape, output routing, and diagnostic mode — nearly everything an agent needs to invoke it correctly. Minor gaps remain, such as the exact shape of the listSheetsOnly response and failure behavior when none of the three input sources is provided.

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 100% so the baseline is 3, but the description adds substantial meaning the schema lacks: the full mappingJson spec structure (conditionalValues with {sourceColumn,matches[],values{}}, staticValues, deduplicateOn, autoGeneratedFields as array or sheet-keyed object with a concrete example) and the semantic consequence that those fields get removed. It also enriches the format parameter by mapping it to downstream consumers (dmf_import_file vs odata_upsert_rows), which the bare 'csv or json' schema text does not provide.

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 opening sentence names a specific action (transform), resource (multi-sheet .xlsx), mechanism (data-driven JSON mapping), and outcome (DMF-ready rows). It anchors the tool as the offline equivalent of FO_TransformExcelForDMF, and the output-routing sentences ('feed to dmf_import_file' / 'feed to odata_upsert_rows') keep it clearly distinct from the import/upsert siblings in the same DMF family.

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 description tells the agent exactly what to do with the result — CSV goes to dmf_import_file, JSON goes to odata_upsert_rows — and states when the tool applies ('NO FO credentials required (offline transform)'). It also explains the diagnostic mode (listSheetsOnly=true) and the 'one of three inputs' constraint. It never explicitly names a when-not-to-use alternative, but the pipeline routing effectively positions it against its siblings.

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