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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine context beyond that: the corpus is German-only, the query language, and the unusual fixed opening phrase "Steiner hat gesagt:" in the reply. It still says nothing about how the grouped counts are shaped or ordered.

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?

Four short sentences, front-loaded with what is counted and how it is grouped, then use case, then query syntax, then reply format. Nothing is repeated and no sentence is 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?

With no output schema, the description carries the burden of return-value context and does partially: it states results are counts grouped by year/volume/place and flags the fixed reply prefix. The remaining gap is the exact structure of the grouped result (per-group counts, ordering), which an agent would still have to discover.

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%, so ga, date_from, date_to and group_by are already documented, and the description does not elaborate on them. It does add meaningful syntax rules for the required query parameter (all words must occur, quoted phrases, OR, -excluded) that the schema's one-line example does not convey, so it earns slightly above the baseline.

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 names a specific verb (counts), a specific resource (passages, plus chapters/lectures), and the three grouping modes (year, volume, place). That is enough to distinguish it from a passage-returning tool like search or read, though it never names a sibling explicitly.

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 use case – questions such as when Steiner spoke most about a topic – which tells the agent this is an aggregation tool for trend questions. It offers no when-not guidance or explicit pointer to search/read for retrieving the actual passages.

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