SRG SSR Polis – Schweizer Abstimmungen

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

Annotations already cover read-only, idempotent, non-destructive. The description adds valuable behavioral context beyond annotations: data goes back to 1900, the canton filter resolves to a locationid, and a year range translates into multiple queries because it maps to voting days – this is non-obvious and affects expectations. It also discloses pagination bounds (page_size 1–100). This goes beyond what annotations provide, though it doesn't cover rate limits or auth, which are likely irrelevant for this read-only endpoint.

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 efficiently structured with XML-style tags that front-load the purpose, then the use case, important notes, and example. Every sentence earns its place – there is no filler. The <example> provides a concrete invocation that reinforces the parameter semantics. The length is justified by the density of operational details.

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 list-fetch tool with an output schema and annotations covering safety, the description is nearly complete. It covers purpose, usage, behavioral nuances, and parameter effects. The only minor gaps are the lack of explicit mention of the response's pagination structure or the meaning of 'openWorldHint', but those are not essential for correct invocation given the output schema exists. Overall, an agent has enough to call it correctly.

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 0%, so the description must compensate. It explains the semantics of canton and year_from/year_to (how they get resolved), and mentions page_size's range. However, it does not explicitly explain the 'page' parameter or the default behavior of each parameter individually. The example clarifies usage but does not fully cover all parameters. It adds meaningful meaning for the two core filters but leaves page and page_size under-described, so a 3 is appropriate.

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 specific verb ('Ruft ... ab') and resource ('Schweizer Volksabstimmungen und Referenden aus dem Polis-System'), and lists the returned fields (Datum, Titel, votation_id). It explicitly distinguishes itself from srgssr_polis_get_elections and positions itself as the prerequisite for srgssr_polis_get_votation_results, so an agent can tell it apart from siblings.

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 <use_case> tag gives concrete contexts (historical analysis, journalistic research) and explicitly states when NOT to use it ('Für Wahlen ... stattdessen srgssr_polis_get_elections'). It also provides operational guidance in <important_notes> about filter behavior (canton→locationid, year→voting days) and pagination limits, leaving no ambiguity about when to select this tool.

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