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

Well beyond what the annotations provide: pricing ($0.005/call), payment rail (USDC on Solana via x402), and the exact two-step invocation pattern (call unpaid to receive the PaymentRequired challenge, then retry with the payment in _meta["x402/payment"]). That is genuinely actionable behavior an agent could not derive from readOnlyHint/openWorldHint alone. It does not explain the result shape, but the payment flow — the real operational risk here — is fully disclosed.

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 purpose in six words, then the cost, then the payment mechanics, then the HTTP mirror — a sensible priority order with no filler. The endpoint URL is long but earns its place for agents that may fall back to HTTP.

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 3-required-param tool with no output schema, the payment protocol is covered thoroughly, but the description leaves the return value (numeric unit? string? rounded?) and accepted unit vocabulary entirely unaddressed. Those are the two things an agent most needs beyond the already-covered billing flow.

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, and the schema descriptions are bare ("From unit", "To unit", "Value"). The description's category list does help narrow what strings 'from'/'to' accept, but it adds no syntax, alias, or format guidance (e.g., whether 'lbs'/'pound' both work, or that 'value' is a string).

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 ("Unit conversion") and enumerates supported domains (length/weight/temp/volume/data/speed), which lets an agent distinguish it from devutils_fx_convert, devutils_time_convert and devutils_color_convert by exclusion. It stops short of naming those siblings explicitly, so the separation is inferred rather than stated.

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 category list implies scope (no currency, no color, no timezone), and the HTTP equivalent hints at an alternate access path, but there is no explicit "use this instead of X when Y" guidance and no statement of when the tool is inappropriate. Usage must be inferred from the parenthetical.

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