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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description adds context the annotations cannot: the jurisdictional limit, that the template uses roles rather than third-party names, and that case facts never go into the tool. That last point is slightly ambiguous next to required parameters like verstoss and datum_vorfall, but it does not contradict 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?

Scope and content inventory are front-loaded in the first two sentences, then usage and privacy rules follow. It is dense but earned; the one weak sentence is the trailing "The facts themselves never go into this tool", which is vague without the surrounding context.

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?

An output schema exists and annotations cover the safety semantics, so the description only needs to convey purpose, scope and the content delivered, which it does. The one residual gap is the unclear relationship between the "no facts in this tool" statement and the required incident parameters.

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% and every parameter carries a bilingual description and enums, so the schema does the heavy lifting. The description's enumeration of required letter parts (Rüge with date and time, verletzte Pflicht, Hinweis, Warnung vor Kündigung) implicitly maps to parameters such as uhrzeit and pflicht_aus, but it never makes that mapping explicit, so it adds only marginal meaning beyond 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?

Specific resource (Abmahnung) with an explicit statement of what it returns: required parts, a template with placeholders, writing rules, checklist and pitfalls, plus a clear domain scope (German employment law, Germany only). It is distinguishable from neighbouring tools by the Abmahnung-vs-Kündigung subject matter, but it never names the adjacent siblings (e.g. kuendigungsschreiben) to sharpen the boundary.

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?

"Use it when an employer wants to warn an employee about misconduct" gives a clear triggering condition, and "German employment law, Germany only" plus the role/naming rule set usage constraints. There is no explicit exclusion or pointer to the alternative tool to use for a termination letter or for a documented employee talk, so the routing is only half-specified.

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