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

The annotations already declare a safe, read-only, idempotent, closed-world operation, but the description still adds real context: it returns aggregated channel counts only (kanal_bezeichnung, zaehlung, je_kanal_summen.personaldienstleister), plus 7-day new discoveries and a trend, with no individual postings and no view. It also discloses how the website presents the numbers (rounded as 'über X') and requires stating the gebiet explicitly in the answer.

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?

Purpose is front-loaded and every clause carries information, but the core text is one very long run-on sentence dense with field paths, which makes it harder to parse than a few shorter sentences would be. No filler, though.

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 an output schema and full annotation coverage already in place, the description supplies exactly what those structured fields cannot: scope (aggregates only, no postings), comparison guidance, the meaning of the channel fields, rounding conventions, and a required disclosure of the counted area. Nothing an agent needs to call or report it correctly is 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 100%, which sets a baseline of 3, but the description adds meaning the schema doesn't: the counts exclude title and location filters, leaving funktion as the only narrowing dimension, and gebiet reflects the counted area that must be echoed back. That reframes how the two parameters interact.

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 states a specific measured object (counts of active job postings across the whole market, without title or location), names the counting source (Stellen-Radar), and explicitly contrasts itself with stellen_finden for single positions or regions. An agent can tell exactly which sibling to pick.

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?

It gives an explicit rule: use this tool for general labor-market questions or as a comparison; use stellen_finden for a position or region, with the added note that its channels are directly comparable. Both the positive and the negative case are covered.

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