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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: it follows standard CSV quoting rules, handles embedded commas/quotes/line breaks, and explains the header behavior. It also cites the source, which is a nice transparency touch. It doesn't mention error handling for malformed CSV, but that's a minor gap given the annotations.

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 sentences with no fluff. The core action and output are front-loaded, followed by the key behavioral details (quoting rules, header modes) and a source citation. Every sentence earns its place.

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?

The tool is simple (2 params, 1 required) and has a rich schema plus an output schema. The description covers the conversion behavior, quoting rules, and header modes. It doesn't explicitly describe the return value shape, but the output schema exists and the description says 'JSON array', which is sufficient. A minor gap is the lack of mention of error handling for invalid CSV, but overall it's complete enough for an agent to call correctly.

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 schema already documents both parameters ('csv' and 'firstRowHeaders'). The description adds a bit of context by explaining the header behavior in prose, but it largely mirrors the schema. Baseline 3 is appropriate because the schema does the heavy lifting and the description doesn't add significant new meaning beyond what's already in the schema.

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 description states a specific verb ('Convert'), a clear resource ('CSV text'), and the output ('a JSON array'). It also distinguishes the two modes (headers on/off) and references standard CSV quoting rules, making the tool's purpose unambiguous. The sibling list includes hopi_json_to_csv, and this description clearly identifies the direction of conversion, so an agent can tell them apart.

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 explains the two header modes and the quoting rules, which tells an agent when the tool is appropriate for CSV parsing. It does not explicitly name alternatives or state when not to use it, but the context of a large sibling list of converters makes the purpose clear enough. A small gap: no mention of edge cases like empty input or malformed CSV, but the schema's minLength covers empty input.

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