Inspect tile

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real behavioral context beyond that: it explains the dual source-resolution model (style source id vs. a TileJSON/PMTiles/tile URL), discloses supported formats (MVT and MLT), and notes it reports metadata layers that the tile lacks — a non-obvious diagnostic behavior.

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?

Roughly four sentences, front-loaded with the what-then-what-you-get, then usage, then source resolution, then formats. Dense but every clause carries information. Minor redundancy between the return-value sentence and the param semantics of 'source', which slightly dilutes sharpness.

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 no output schema, the description correctly carries the full burden of explaining the return shape, and does so thoroughly (layer list, feature counts, geometry types, field values, examples, zoom range, missing layers). All eight parameters are documented in the schema, and the non-obvious 'source' semantics are covered in prose. Nothing an agent needs to invoke it correctly is absent.

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 description coverage is 100%, so the baseline is 3. The description adds genuine meaning on top by clarifying that 'source' accepts either a style source id or a vector-source URL and naming the concrete URL forms (TileJSON, PMTiles, {z}/{x}/{y}), which the schema's brief 'id of a source in the style, or the URL' does not fully spell out.

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 and resource ('Reads the vector tile of a source at a place and zoom') and then enumerates exactly what it returns — source layers, feature counts, geometry types, field values, examples, and the source's zoom range. This is detailed enough to distinguish it from siblings like describe_sources and debug_layers, which operate at a different level.

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?

Explicitly states the motivating context: 'Use it to learn the values data really has, like the classes of roads, before writing filters and expressions.' That is a concrete when-to-use. It stops short of naming which sibling to use instead when the agent only wants metadata or validation, so it lacks the explicit alternative-routing of a 5.

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