Buildings near a point

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is fully covered. The description adds valuable behavioral context beyond annotations: it discloses the no-raw-geometry-by-default design rule, the include_geometry=true caveat with token cap and geometry_max_deviation_m reporting, and the structured error behavior when upstream is unavailable or dataset is missing geometry/bbox. That is more than annotations provide. Not a 5 because it doesn't mention pagination or ordering ties, but the disclosed behaviors are meaningful.

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 moderately sized but every sentence earns its place: the return shape, the no-geometry design rule, the include_geometry consequences, and the error case are all covered. It front-loads the core purpose and leads with the most important semantic ('nearest first'). Slightly dense parenthesis nesting costs a little readability.

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?

Given annotations cover safety and idempotence, the output schema is explicitly illustrated in the description, and the tool is a simple point-query with 5 params, the description is complete. It even discloses edge cases (upstream unavailable, missing geometry/bbox) and the design rule behind default behavior. An agent can call this correctly without additional documentation.

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 0%, so the description carries the full burden. It explains include_geometry in detail and implies radius_m and limit via 'nearest ... nearest first', but doesn't specify units for radius_m (meters are inferable from the name), default/range semantics, or limit semantics beyond a list length. With 5 params at 0% coverage, a 3 is the minimum viable; the description compensates for the most important parameter but leaves lat/lon/radius_m/limit to 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?

States a specific verb+resource ('Nearest building footprints to a point, nearest first') and differentiates from siblings: it's clearly a point-query tool (like infrastructure_at, land_use_at, water_near) targeting building footprints. The scope is unambiguous: buildings near a point, not places, infrastructure, or areas.

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 explains the design rule ('answers, not data') and the optional include_geometry behavior, giving context for when to use the default versus when to pass the flag. It doesn't explicitly name alternatives or exclusions like infrastructure_at for non-building features, but the phrasing 'building footprints' and the sibling list imply the boundary. Slight gap: no explicit 'use X for other features' guidance.

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