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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the bar is lower; the description still adds genuine behavior beyond them by explaining the internal routing to one country-specific partition and disclosing a real failure mode ('broad views may require zooming in'). It does not describe cost, latency, or what happens when the rectangle straddles partitions, but the output schema covers return shape.

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 routing behavior front-loaded and the input requirement and caveat following — no filler. The density of unexplained internal jargon ('Admin 1-6 spine', 'Admin 1-owned exact partition') costs a point because an unfamiliar agent must decode terms that are never defined.

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?

For a read-only, idempotent resolver with a full input schema and an output schema, the definition covers purpose, precondition, input provenance, and one operational caveat, which is close to sufficient. It is only short of a plain statement of the result (what the deep partition comparison yields) and of how it relates to its named siblings.

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 the baseline is 3, but the description adds two constraints not in the schema: the corners must be the 'original' four (i.e., not narrowed from the shallow call) and they are WGS84, which the schema never states. It adds nothing about request_id, which is fine since the schema documents it as an optional tracing ID.

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 names a specific operation (a second-pass rectangle overlap resolved against a single shallow administrative loc_id) and explicitly frames it as the deep counterpart to a first shallow pass, which distinguishes it from resolve_bbox and resolve_deep_point. The wording is domain-dense ('Admin 1-owned exact partition', 'Admin 1-6 spine'), so an agent gets the shape of the operation but not a plain-language statement of what it returns.

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?

'Second-pass' and 'within one returned shallow administrative loc_id' establish that this tool must be called after a shallow lookup and scoped to one of its results, which is real sequencing guidance. However, the prerequisite sibling (resolve_bbox) is never named, and there is no explicit statement of when to skip the deep pass or what to do if the shallow result is absent — the agent must infer the call order.

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