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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered. The description still adds real behavioral context by disclosing that results come back as a best overlap plus nearby matches at each level with share-of-viewport and share-of-loc_id figures, and by warning that oversized views may need zooming. It does not say what happens to matches outside the viewport or how partial overlaps are ranked, leaving the ranking behavior opaque.

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?

The opening sentences front-load the comparison and the required input efficiently, and the return-shape sentence is informative. The closing line, 'This tool reads no country deep bank,' is unexplained internal jargon that costs space without giving the agent an actionable rule, and 'Large views may require zooming in' is too vague to guide a retry strategy.

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 full schema coverage, an output schema, and complete annotations, most of the burden is carried elsewhere, and the description fills in the comparison target and the resolution limits. The notable gap is sibling routing against resolve_deep_bbox and resolve_point, which matters given three similar-sounding resolve tools. Otherwise an agent has enough to call this correctly.

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 both corners and request_id are already documented, including the four-distinct-corners and antimeridian constraints. The description mirrors that with 'Supply its four corners' and 'non-wrapping' but adds no format, ordering, or tolerance detail beyond the schema. Baseline 3 is appropriate when the schema carries this much weight.

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 gives a specific verb and resource: compare one non-wrapping rectangular WGS84 viewport against the Global administrative spine through Admin 2, and return best equal-area overlap plus nearby matches. That is far more than a restatement of the name. It stops short of naming a sibling such as resolve_deep_bbox or resolve_point, so the agent must infer the split from the domain wording alone.

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?

Usage is implied by the constraints: supply four corners, views must not cross the antimeridian, and large views may need zooming in. There is no explicit guidance on when to pick this over resolve_deep_bbox or resolve_point, which is the main routing decision an agent faces here. The closing line about the 'country deep bank' gestures at a boundary but does not state a rule the agent can act on.

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