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

Annotations already declare readOnly, idempotent, non-destructive, openWorld. The description adds genuinely new behavioral context: a $0.001 USDC per-success x402 charge, an HTTPS fallback endpoint, exact-rational results, and a rejection rule for raw radians. Only the shape of the returned value is left unstated.

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?

The purpose and unit conversion factors are front-loaded in the first sentence, and the constraint follows. The geometric explanations (1/360 turn, half a turn) are mildly educational overhead but do justify the unusual pirad unit; the pricing/endpoint line is compact and relevant.

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 no output schema and zero parameter description coverage, the description should close more gaps than it does. It covers cost, endpoint, units and rejection rules well, but leaves both the input string format and the returned representation (exact rational as what?) unexplained for a tool whose entire contract is a value in, value out.

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 0% and the single 'value' string parameter is undocumented in the schema, so the description carries the burden. It lists the legal units and rules out radians, but never shows the input format (e.g. "90deg" vs "0.25turn") or whether a target unit can be specified, leaving the caller to guess.

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 and resource — convert a CSS angle among deg, grad, turn and pirad — and enumerates the supported units, so an agent can tell it is not css_length or css_time. It stops short of naming a sibling alternative (e.g. unit_convert), which is the only thing separating it from a 5.

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 domain: use it when you have a CSS angle to convert. There is one useful negative constraint ("A raw radian value is rejected because π is not rational"), but no explicit statement of when to prefer unit_convert instead, nor guidance on valid input formatting.

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