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

Goes well beyond the annotations: RFC 4180 parsing guarantees, typed number/boolean coercion with a typed=false escape hatch, and full commercial terms ($0.005/call over x402 on Base, x-credit-token header, 1 free call/day, no API key). The 'no upstream, local parsing only' claim sits uneasily with openWorldHint=true, but the x402 payment path plausibly accounts for that hint, so it is not a direct contradiction.

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 conversion matrix before the guarantees and the payment terms, so the agent gets the point in the first clause. It runs long, however, with roughly a third of the text devoted to pricing/free-tier marketing that is only tangentially about invoking the tool.

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?

With an output schema present it correctly does not describe return values, and it covers formats, type handling, and cost/auth. It omits failure behavior — what happens on malformed CSV or oversized input — which matters for a parser advertised as strict.

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 real meaning: it names the required inputs (text, from, to), lists the concrete format vocabulary for from/to, and explains typed defaults to true and is disabled with typed=false — the schema only says 'Type numbers/booleans (optional)'.

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?

Names the verb (convert) and enumerates the exact resource pairs handled: CSV/TSV→JSON, JSON→CSV/TSV, CSV→Markdown, Markdown→HTML. An agent can distinguish this from unit_convert, fx_convert, url_to_json or bank_csv purely from the text.

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?

Usage is implied by the format pairs and by 'No model call and no upstream: local parsing only', which tells the agent this is a deterministic local transform. But it never states when to prefer this over siblings like url_to_json or bank_csv, and gives no exclusions or prerequisites beyond payment.

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