Backup Health Summary (Flotte)

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description is free to add substantive behavior: it returns ONLY problem cases, skips archived agents, splits findings into critical vs warning, and states the default thresholds. That is real operational context beyond the annotations, though it omits things like result format or performance/rate considerations.

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 purpose, then the critical conditions, the warning conditions, the skipping rule, and the defaults in a logical order. It is dense and long, but nearly every clause carries distinct information; only minor tightening would be possible.

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 no output schema, the description carries the return-value burden and does so by enumerating the finding categories and the 'only problem cases' behavior. Given 11 optional parameters and no required ones, plus the threshold defaults provided, an agent has enough to call it correctly, though it never describes how findings are grouped or returned.

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 low (45%), so the description must compensate, and it does: it supplies the defaults for snapshot (24 h), offsite (48 h), screenshot (7 d), offline (1 h), storage (85 %) and service contract (30 d), effectively documenting the six numeric parameters that have no schema description. This is exactly the parameter meaning the schema is missing.

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 and resource: it checks all devices/agents against thresholds and returns only problem cases, then enumerates the exact critical and warning conditions. This is precise and self-contained, but it never names or contrasts with overlapping siblings such as get-screenshot-failures or list-alerts, so the agent must infer the boundary itself.

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?

Usage is implied by the scope ('alle Geräte', 'NUR Problemfälle') and by the list of conditions, which tells the agent when a device will surface. However, there is no explicit when-to-use vs when-not guidance and no alternative tool named, so selection against list-alerts or get-screenshot-failures is left to inference.

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