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

Annotations declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, and the description adds substantial context beyond them: no hosting changes, no result link because the scan lives in the agency account, no runtime guarantee, and the response reports the actual reported state rather than always saying 'gestartet'. This is unusually rich disclosure for a mutation-flavored tool.

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?

Front-loaded with the action, and each sentence carries a distinct fact (scope, result path, stale score, no link, honest state reporting, no runtime promise). It is somewhat long and repeat-referencey for a one-parameter trigger, which keeps it short of a 5.

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 trigger tool in a multi-step flow with no output schema, the description supplies everything an agent needs: how to read the result, why the score lags, why there is no link, and that completion is discovered via the timestamp on get_performance_findings. Nothing material 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 description coverage is 100% and there is only one parameter (domain), so the schema already carries the semantics. The description adds nothing domain-specific; baseline 3 is correct when the schema does the work.

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 specific verb (anstoßen/start) plus the resource (Performance-Scan) and the explicit contrast case (statt auf den nächsten automatischen Lauf zu warten). The sibling landscape contains many get_performance_* readers, and this one is clearly demarcated as the trigger rather than a reader.

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?

Tells the agent when to use it (instead of waiting for the automatic run) and routes the follow-up explicitly: results come AUSSCHLIESSLICH from get_performance_findings, while get_performance_score stays stale until the nightly report. That is an explicit alternative/next-step with conditions attached.

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