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

Annotations declare readOnlyHint=true, and the description reinforces a safe read operation without contradiction. Beyond that, it discloses meaningful behavioral guarantees: 'This never invents a parent edge across mixed releases,' the configurable cap on loc_ids, and the semantics of include_hierarchy vs include_references. This level of detail exceeds what annotations alone provide.

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 description is dense but not bloated; each sentence contributes a distinct piece of information (purpose, input modes, flags, alternatives). It front-loads the core purpose before detaling options. It could be slightly trimmed, but the structure is logical and scannable.

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 an 11-parameter tool with no output schema, the description provides a comprehensive overview: what it returns, how the two input modes work, the meaning of the two key flags, and clear routing to siblings. The schema covers the remaining parameter details. Missing an explicit list of return fields is mitigated by the upfront enumeration of metadata categories.

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. The description adds value by clarifying the loc_id/loc_ids usage ('pass one loc_id, or pass the point result's stack loc_ids together') and explaining defaults like the 'Default public cap is deployment-configurable.' It also frames include_hierarchy as 'strict same-release ancestor chain,' which is not in the schema. These additions justify a 4.

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 opens with a clear verb-resource pair ('drill-down tool for loc_ids') and enumerates exactly what it returns: metadata, strict stored parentage, shape status, vintage/lifecycle fields, and child counts. It distinguishes itself from siblings by naming resolve_point, get_geometry, and compare_geographies explicitly, leaving no ambiguity about scope.

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?

It explicitly states when to use it ('This is where detailed chain explanation belongs; resolve_point intentionally stays compact') and when to prefer alternatives ('For exact polygons use get_geometry, and for overlap or successor analysis use compare_geographies'). It also notes 'No payment required,' which is a practical usage condition.

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