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

Discloses substantial behavior beyond the sparse annotations: type preservation in both directions with concrete examples (numbers stay numeric, blanks become true nulls, '01924' keeps its leading zero), and explicit handling of nested/repeated columns as reported rather than silently flattened. No contradiction with readOnlyHint=false or destructiveHint=false.

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?

Three sentences with no waste: scope, behavioral guarantees with concrete examples, then the schema-shape constraint. Purpose is front-loaded before caveats, and the 'Parquet Converter —' opener anchors the reader before the action verb.

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 a 4-parameter bidirectional converter with a fully covered schema, the definition is nearly complete: purpose, type behavior, and schema limitations are all addressed. The only gap is that the return value is never described (file download, link, etc.), which matters more given there is no output schema.

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 100%, so the baseline of 3 applies; the schema already documents to, file, from, and sheet thoroughly, including the jsonl alias and the convert_data routing note. The description's type-preservation examples add background context for format choice but do not map to any specific parameter's usage.

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 action and resource — converts Apache Parquet to/from CSV, TSV, JSON, NDJSON, and Excel — with 'and back' making the bidirectional scope explicit. The flat-schema-only constraint further distinguishes it from generic table converters, so an agent can tell it apart from the many convert_* siblings without opening the schema.

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 format list clearly defines when to use it (any conversion with Parquet on one side), and 'flat schemas only' is a stated when-not condition. It never names alternatives in the description itself, though the schema's to-parameter description compensates by routing table→table pairs to convert_data; full coverage of siblings like convert_file and convert_batch is absent.

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