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

Annotations already declare the safety profile, but the description adds genuinely useful non-annotation context: the $0.001 USDC cost on Base, x402 payment, and that it is charged only 'per successful call.' That pricing/auth detail is exactly the kind of behavior an agent must know before calling an openWorld paid endpoint.

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 short sentences, purpose front-loaded ahead of the cost disclosure, with no redundancy. 'Use for dates, outlines and puzzles' is the weakest sentence and edges toward filler, keeping it out of the top band.

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 two-parameter pure conversion tool with no output schema, the description covers direction, input range, mutual exclusivity, and payment. The only real gap is that it never says what comes back (Roman string vs. integer) or how out-of-range input is handled.

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; the schema already documents both parameters and the 1-3999 range. The description's 'Give either number or roman' adds a mutual-exclusivity hint that the schema does not encode (both params are optional with no oneOf), so it is slightly above pure repetition but not rich.

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 with explicit bidirectional scope: 'Convert a number (1-3999) to Roman numerals, or Roman numerals back to a number.' The 1-3999 bound makes it distinguishable from the nearby number_words sibling, but that sibling is never named or contrasted.

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?

'Use for dates, outlines and puzzles' implies usage context but gives no when-not guidance and no reference to alternatives such as number_words. It also tells the agent to supply one of two inputs ('Give either number or roman'), which is invocation help rather than selection help.

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