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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, and the description still adds substantive behavior: what it will not include (buildings, roads, terrain, constraints, ownership), that SVG output is illustrative and not to scale, and that projected coordinates are rejected until reprojected to WGS84. Those validation and limitation rules are exactly the kind of context annotations cannot express.

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?

Labeled sections (Purpose, When to use, Returns, Limitations, Parameter guidance, Chaining) front-load the decision-critical facts before detail. The 'Returns' sentence is partly redundant with the existing output schema, but it is one clause and does not bloat the definition.

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 a validator/exporter with a nested site_ref, a low-coverage schema and an output schema already present, the description covers the preconditions (WGS84, 2D, user-supplied geometry), the negative cases, and the chaining contract. Nothing an agent needs in order to call it correctly appears missing.

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 only 25% and boundary_geojson is declared as an untyped empty object, so the description has to carry the load — and it does, specifying WGS84 2D geometry accepting Polygon/MultiPolygon/Feature, the geojson/svg format choice, optional title, and the chain-through rule for site_ref. It stops short of concrete input examples or coordinate-order (lat/lng vs lng/lat) guidance, which matters for a geometry payload.

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 concrete verb pair and resource: 'validate and export a supplied WGS84 boundary as GeoJSON or SVG'. The validator/exporter framing combined with the input (user-supplied boundary) distinguishes it cleanly from siblings like export_site_context or generate_site_map, which produce derived artifacts.

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?

Gives an explicit when-to-use trigger ('user provides a Polygon, MultiPolygon or Feature and wants a portable boundary file') and an explicit exclusion ('Do not invent a boundary from an address'). It never names a sibling alternative for the adjacent cases (e.g. generate_site_map for a rendered map, export_site_context for workspace export), so routing between near-neighbors is left partly to inference.

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