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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds contextual behavior: it queries 'inside a Mapbox vector tile around a coordinate' with 'a radius of a point,' and is 'against a specific tileset_id.' This goes beyond the annotations by describing the spatial scope and specialization. It doesn't contradict annotations. Some behavioral details (e.g., exact feature types returned) are covered by the output schema, so a 4 is appropriate.

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 two sentences and front-loaded: the first sentence states the core function and scope, the second adds specialization and alternatives. Every word earns its place, with no repetition of schema or annotations. It is concise while carrying significant meaning.

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 tool has 8 parameters and is specialized, but the output schema exists and annotations cover safety and idempotency. The description explains what the tool does, what types of features are relevant, the need for a tileset_id, and when to prefer alternatives. It does not enumerate all parameters, but the implicit coverage plus output schema reduces the need. Given the complexity, it is mostly complete, though not exhaustive—hence a 4.

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?

The schema provides zero descriptions (0% coverage), so the description must compensate. It covers several key parameters implicitly: lat/lon ('around a coordinate'), radius ('within a radius of a point'), tileset_id ('specific tileset_id'), and layers ('POIs / roads / boundaries / buildings'). However, it does not address limit, dedupe, or geometry, and with 8 total parameters the coverage is partial. This is similar to the update_drive case where schema coverage is incomplete, warranting a 3.

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 starts with a specific verb+resource: 'Query features inside a Mapbox vector tile around a coordinate,' and further elaborates with example feature types (POIs, roads, boundaries, buildings). It explicitly distinguishes itself from siblings by calling it a 'Specialized GIS query' and noting that 'most users want geocode_reverse or directions instead.' This clearly differentiates it from the listed geocoding and routing tools.

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 explicitly gives usage context: it is for querying vector tiles by a coordinate and radius, restricted to a specific tileset_id. It also provides an explicit when-not-to-use: 'most users want geocode_reverse or directions instead,' naming the preferred alternatives for typical use cases. This is actionable guidance beyond what any structured field provides.

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