swisstopo_oereb_at

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint, and openWorldHint. The description adds valuable behavioral context beyond these: it is a single call ('ein Aufruf'), it resolves the EGRID internally, and it is restricted to cantons with a connected ÖREB service. It also notes coordinate formats. However, it does not clarify behavior when both coordinate systems are provided or what happens for unsupported cantons.

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 well-structured with distinct use_case and important_notes blocks. The main sentence is front-loaded and direct. Each sentence provides actionable information, such as the EGRID resolution, the alternative tool, and coordinate format requirements, without any filler.

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 is relatively complex with multiple parameters, coordinate systems, and an output schema. The description covers the primary use case, internal EGRID resolution, cantonal availability, and coordinate formats. The output schema is present, so return structure need not be described. However, it omits topics and language parameters, which are only in the schema, and does not address edge cases like no coordinates provided or conflicting coordinate systems.

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 description provides essentially no parameter documentation (0% coverage), but the input schema itself has detailed descriptions for each field (e.g., lat: 'Breitengrad (WGS84). Zusammen mit lon angeben.'). The description's note about lat/lon or easting/northing and the cantonal restriction adds a bit beyond the schema, especially the requirement that the canton must have an ÖREB service. Still, the description does not compensate for the low coverage; it relies on 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?

The description clearly states the tool's function: 'Gibt die ÖREB-Eigentumsbeschränkungen an einer Koordinate zurück' (returns ÖREB property restrictions at a coordinate), with a specific verb, resource, and scope. It also distinguishes from sibling tool swisstopo_get_egrid by explaining that this tool resolves EGRID internally and is the normal way, while get_egrid is only for needing the parcel ID itself.

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 provides explicit usage context via the use_case block: '«Welche Beschränkungen gelten auf diesem Grundstück?»' and states 'Das ist der normale Weg; swisstopo_get_egrid braucht es nur, wer die Parzellen-ID selbst benötigt.' This gives clear when-to-use and when-not-to-use guidance, names an alternative, and also specifies a precondition: 'Nur für Kantone mit angebundenem ÖREB-Dienst'.

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