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

Adds genuinely useful context beyond the annotations: millimetre accuracy for Vincenty, offline/deterministic behaviour, affordability of multiple calls, and explicit cost ($0.001 USDC per successful call via x402 on Solana) plus an HTTPS fallback endpoint. Minor tension: 'Offline, deterministic' sits awkwardly against openWorldHint=true, though that hint likely reflects the paid remote service rather than data lookup.

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?

Operations are front-loaded in one dense but well-ordered clause, followed by units, then a separated pricing/endpoint line. It is long and somewhat run-on, but every clause (accuracy, units, payment, HTTPS alias) carries information an agent needs.

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, the description partly compensates by naming outputs (16-point compass bearing, per-segment legs, midpoint). However, with zero required parameters it never explains the mutually exclusive input combinations or the failure mode when no mode inputs are given, leaving the most consequential ambiguity unaddressed.

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 83%, so the schema already documents most params; the description adds the units vocabulary and clarifies that 'points' yields total length plus per-segment legs and that 'bearing'+'distance' trigger destination mode. It doesn't explain the 'lat,lon' string format limits or how overlapping inputs are resolved, so slightly above baseline only.

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 opens with a precise verb+resource ('Geodesic distance and bearings on the WGS-84 ellipsoid') and enumerates the distinct computations: Vincenty/haversine distance, initial/final bearing, midpoint, multi-point path length with legs, and destination-from-bearing. An agent can immediately tell this apart from siblings like coord_convert, geo_polygon, or cosine_law.

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?

Mode selection is only implied by pairing operations with inputs ('the destination point from a start, bearing and distance'; 'Path: list of lat,lon'). There is no explicit when-to-use guidance, no statement of what happens if several or no mode inputs are supplied (all 6 params are optional), and no comparison to nearby tools such as coord_convert or geo_polygon.

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