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

With no annotations, the description carries the full burden and does meaningful work: it discloses cost ($0.003 USDC/call), the payment protocol (x402), the chain (eip155:8453), and the important billing rule 'No match = not charged.' It doesn't state how ambiguous addresses are resolved (single best match vs. candidates), required wallet/auth preconditions for x402, or rate limits.

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?

A single dense sentence with the cost/chain metadata bracketed up front and the capability plus edge-case billing rule following. No filler, nothing repeated, and the most decision-relevant info (price, US scope, no-charge on miss) is front-loaded.

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?

There is no output schema, so the description correctly compensates by enumerating the returned fields and noting GEOIDs are official. For a one-parameter tool this is nearly complete; only multi-match/ambiguous-address behavior is left unspecified.

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% and the schema already gives a format example ('350 5th Ave, New York, NY 10118'). The description reinforces 'one US street address' but adds no additional syntax, normalization, or failure-mode guidance beyond the schema.

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?

Specific verb + resource ('Geocode one US street address'), names the data source (U.S. Census Bureau), and enumerates the exact outputs returned (lat/lon, tract, block group, ZCTA, GEOIDs). The 'US street address' scoping also implicitly separates it from uk_postcode in the sibling list.

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?

Clear context: single-address, US-only geocoding, so an agent knows not to route Canadian/UK lookups or batch lists here. It doesn't explicitly name uk_postcode as the alternative for non-US addresses, nor state what to do with ambiguous/multi-match addresses — the only gap.

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