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

Annotations already mark the tool as read-only and idempotent, so the description's job is to add behavioral nuance. It does: `observed` means first-seen date, not in-force date; the result is JSON; ordering is newest first; and the window is capped at 120 days. This goes well beyond the annotations and helps the agent use the feed correctly.

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, each carrying distinct information: the core function, the polling pattern, and the essential semantic caveat about `observed`. The most decision-relevant content is front-loaded in the first sentence, and there is no filler.

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 simple read-only feed, the description covers the polling model, ordering, date semantics, and window. It does not specify the response object shape, and there is no output schema, so an agent must infer the exact JSON fields beyond `observed`. Still, the description provides enough to call and interpret the tool in most cases.

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 only 50%: `since` is described but `limit` is not. The description compensates for `since` by defining the critical `observed` semantics, which is more precise than the schema's 'on or after this date'. `limit` remains undeveloped, but its name plus schema constraints make it self-explanatory.

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 opens with a precise statement of what the tool does: it returns provisions whose text changed recently, ordered newest first, and identifies itself as a 'freshness feed'. This is a specific verb and resource, and the 'freshness feed' framing separates it from siblings like listNormVersions or search without ambiguity.

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 a concrete polling strategy: set `since` to the newest `observed` value already processed. It also clarifies the 120-day window and notes that the law's own Änderungsverlauf reaches further back, implying an alternative for older changes. It does not explicitly name a sibling tool or state a 'when not to use' condition, but the context is clear.

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