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

The annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description adds the genuinely useful context: ordered results, tiered fallback, and the fact that a successful call consumes one account credit. It says nothing about failure handling or rate limits, which keeps it short of a 5.

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?

Three tight sentences, with the core action front-loaded and each following sentence adding new information: fallback behavior, ordering, and cost. There is no filler.

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?

The description is complete for a four-parameter read-only geocoding tool: it covers what the tool does, how results degrade, result ordering, and the credit cost. Given that there is no output schema, it could say slightly more about the response shape, such as address fields or confidence, but nothing a caller critically needs is missing.

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 lat, lon, size, and radiusM are fully documented, including defaults, ranges, and omission semantics. The description adds no parameter-level detail beyond 'coordinates', so the baseline of 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?

The description states a specific verb ("look up") and resource ("nearest addresses from coordinates"), which clearly identifies the tool's function as reverse geocoding. This makes it distinguishable from siblings such as search and autocomplete by its input domain (coordinates rather than text), although the description does not mention those siblings by name.

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 description implies that this tool should be used when you have coordinates and want addresses, but it never explicitly states when to use it instead of search, autocomplete, or retrieve. The fallback description about streets and localities describes result behavior, not tool selection, so the agent must infer the boundary.

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