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

Annotations already mark this as non-read-only, non-idempotent, non-destructive, but the description adds substantial context the annotations cannot carry: the result is persisted for 24 hours, the response includes storage_id and storage_url, no API key or account is required, and spreadsheet_safe specifically guards against cells a spreadsheet would execute as formulas. That is a strong disclosure of side effects and auth posture for a file-producing tool.

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-loaded with the purpose and the two modes, then layers limits, delimiter, safety, and retention in compact sentences. The final 'No API key, no account and no sign up' is somewhat promotional and repeats itself, but overall the text is dense with useful information rather than padded.

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 six-parameter conversion tool with no output schema, the description covers what is produced (result.csv / result.json), how it is returned (storage_id and storage_url), retention (24 hours), size limits, and the direction-specific parameter split. Nothing an agent needs before invoking it 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 coverage is 100%, so baseline is 3; the description earns above that by explaining what spreadsheet_safe actually does (guards formula-injection-prone cells) and by clarifying the direction-dependent parameter pairing in prose. Limits like 'up to 5000 flat objects' restate schema maximums, which is why it is not a 5.

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 and resource ('Convert between JSON rows and CSV') and immediately distinguishes its two modes by name: json_to_csv takes columns and rows and stores result.csv, while csv_to_json takes data and stores result.json. An agent can tell exactly what the tool does and which direction to pick without inspecting 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?

Guidance is clear at the mode level: it names which parameters belong to which direction (columns and rows for json_to_csv, data for csv_to_json) and states the 5000 flat-object limit. It does not explicitly steer against siblings such as json_check or match_tables, so it stops short of naming alternatives, but the internal routing guidance is solid.

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