search_rooms

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

Annotations already cover safety (readOnly, idempotent, non-destructive) and openness, so the bar is lower, yet the description adds genuinely non-obvious behavior: no TUMonline token is required, and the default result set spans all campuses including Heilbronn, which would otherwise surprise an agent filtering for Garching. It omits the 20-result cap behavior and whether results are ranked or mixed across entity types.

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 compact sentences, each carrying distinct information: what is searched, the auth fact, and the default scope plus how to narrow it. The filtering instruction is placed last where an agent will act on it, and nothing is redundant.

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 three-parameter, no-output-schema search tool this is close, but gaps remain: the description does not say whether results are a mixed list of rooms/buildings/sites or differentiated by type, nor how truncation at 'limit' behaves. Those are the details an agent needs to interpret what comes back and whether to re-query.

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 0%, so the description must carry the parameter burden. It does well on 'campus', explaining it takes a NavigaTUM parent id and giving 'heilbronn' and 'garching' as examples; but 'query' and especially 'limit' (bounded 1-20) get no semantic treatment, leaving two of three parameters documented only by their JSON types.

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 specific verb+resource ('Search rooms, buildings, and sites on NavigaTUM') and even names the backing API endpoint, which clearly separates it from the course/lecture/person search siblings. It stops short of explicitly contrasting itself with the single-entity 'get_room' tool, so differentiation is inferred from the resource rather than stated.

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 useful scope guidance — the default search covers every campus including Heilbronn, and a campus parent id narrows results — which is the main decision an agent faces here. However, it never states when to reach for this versus a sibling such as get_room for detail lookup, and there is no exclusion or prerequisite guidance beyond the token note.

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