bak_isos_by_kanton

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds meaningful context: it explains that the count field counts ISOS numbers, not features, and highlights that a source can return multiple features per site (up to 51 in GR). This clarifies a potential misinterpretation, which is valuable beyond the annotations.

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, front-loaded with the core purpose, and contains detailed but necessary information about parameters and return format. It uses clear German language with a logical flow from purpose, to parameters, to return values. No fluff.

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 the tool's simplicity (1 parameter, annotated as read-only) and the existence of an output schema, the description is complete. It explains the counting nuance and the return structure, leaving nothing critical for an agent to infer. The notes about source behavior (multiple features per site) are essential for correct interpretation of results.

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 minimal descriptions for parameters, but the description compensates by detailing the 'kanton' format (uppercase, examples) and explaining the 'limit' parameter's default and maximum, as well as the implications of limiting. Given that schema description coverage is 0%, the description effectively covers the parameters.

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 verb 'listet auf' (lists) and the resource 'ISOS-Ortsbilder eines Schweizer Kantons'. It provides the unique context of Swiss cantons and differentiates from siblings by focusing on canton-based listing. The scope is specific and unambiguous.

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 that it lists all ISOS sites for a canton and specifies the input format ('ZH', 'BE', 'GR etc.'). Although it does not explicitly mention when not to use it, the tool's purpose is clearly stated, and sibling differentiation is implied by the tool's name and focused resource. The return format and limit behavior are also clearly explained.

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