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

Annotations already cover safety (readOnlyHint, openWorldHint, destructiveHint=false), but the description adds substantial behavioral context they cannot: pay-per-call cost ($0.003 USDC), the x402 payment mechanism and supported chains, automatic payment by clients like @x402/mcp, millisecond latency from an own database, and how out-of-scope input surfaces via ignored_parts. That is uncommon depth for a paid tool.

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?

Purpose is front-loaded in the first clause, followed by coverage, limitations, payment, and a free-sample hint, each in its own sentence. Dense but every sentence carries a distinct fact; the pricing and sample details are long but justified for a paid 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 no output schema, the description still discloses a return-field name (ignored_parts), coverage scope, latency, and payment requirements, so an agent knows what to expect and what it costs. It stops short of describing the general response shape (e.g. place name, country, postal code fields), leaving a small gap for a tool with no output schema.

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 description coverage is 100% and the schema itself carries examples, the oneOf constraint, and limit semantics, so the description has little left to add. The description does reinforce the address-vs-lat/lon choice and gives its own example strings ('Paris, Texas', '10115 Berlin'), but adds no format or constraint detail the schema lacks. Baseline 3 applies.

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 (geocoding / reverse geocoding) and describes both directions of the transform: 'city, town or postal code to lat/lon, and lat/lon to the nearest place and postal code.' An agent can immediately tell this apart from siblings like postal_code or timezone, which do not convert between coordinates and addresses.

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?

Explicitly states the two input modes: 'Provide address (e.g. ...) or lat + lon', matching the schema's oneOf. It also states the scope limitation ('Not street level: house numbers and streets are skipped'), which tells the agent when results will be partial. It does not name sibling alternatives (e.g. postal_code), so it stops short of full when/when-not routing.

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