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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the description only needs to add context, and it does: it discloses the produced artifacts (.xlsx plus .csv, or a ZIP when linked sheets exist), the round-trip verification that every cell was read back from both files, and the numeric/formula text preservation behavior. It also flags the non-obvious refusal cases (no comments, no trailing commas, no JSON Lines) and the deliberate non-coercion of date text into Excel dates.

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?

Front-loads the when-to-use clause before parameters and exclusions, and most sentences carry distinct information. The single long sentence enumerating return values (rows, columns, cells, numbers kept as text, formula-like text, read-back check) is dense and partly redundant with the output schema, which costs it the top mark.

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 7-parameter conversion tool with nested file objects, three enums, and an output schema, the description covers input sources, layout semantics, artifact outputs, verification, and hard input rejections. Nothing an agent needs in order to select and call it correctly — including which input mode to prefer — is missing.

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% and every parameter already carries a detailed enum explanation with examples, so the baseline is 3. The description restates the key knobs (records_path e.g. data.items, orient records/columns/index, scalar_arrays join/rows, object_arrays sheet/json) but adds no syntax or defaulting nuance beyond what the schema properties already say.

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+resource pair (convert JSON to Excel/CSV) and enumerates the concrete scenarios it covers: API responses, JSON exports, and flattening nested JSON. It also draws explicit boundaries against the one sibling domain ("Do not use for Excel to JSON or for editing a JSON file"), so an agent can route between json_to_excel and inspect_json without opening a 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?

Opens with a direct when-to-use clause keyed to user intent ("Use this when the user wants to convert..."), then lists concrete triggers such as pasted json_text versus an attached .json file. It also names explicit exclusions — JSON with comments, trailing commas, JSON Lines — and points to the inverse operation, which is precisely the when-not-to-use guidance the dimension asks for.

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