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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile needs no restating. The description adds real value by previewing the returned payload (duration, preparation, phases with goals and open questions, difficult moments, minutes template, legal traps such as BEM and works council rights). It says nothing about depth limits or how the output varies when `betriebsrat` is set.

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?

Three sentences, front-loaded with the domain and the four meeting types, then usage, then output contents. Dense and essentially waste-free, though the parenthetical German/English glosses add length that the enum already covers.

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, yet the description still sketches the return shape in business terms, which is helpful rather than redundant. With annotations carrying safety, a complete schema, and explicit scope plus audience, an agent has everything needed to select and call this 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 100% and the `art` enum already lists all four values with glosses, so the description's enumeration is largely duplicative. The one genuinely useful semantic – that the company may have a works council and this affects the legal-traps section – is only hinted at via 'works council rights' and never tied explicitly to the `betriebsrat` flag.

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?

Names the specific resource (a Leitfaden for Mitarbeitergespräche) and enumerates the four covered meeting types with German and English labels, which maps directly to the `art` enum. Geographic scope ('Germany only') and the audience ('founder') further pin down what this tool is versus adjacent legal-reference siblings like `abmahnung` or `probezeit`.

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 a founder has to hold such a meeting' gives a clear triggering condition, and 'Germany only' is an explicit exclusion. It stops short of naming an alternative tool or saying when a different sibling should be preferred instead.

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