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

Annotations already cover the read-only safety profile (readOnlyHint=true, destructiveHint=false), so the bar is lower. The description adds the valuable behavioral trait that results are restricted to 'approved and available' rooms. It does not disclose pagination behavior, default ordering (order_by defaults to 'newest'), or that filters are all optional, leaving some behavioral gaps.

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?

A single sentence with zero wasted words, front-loaded with the verb and resource before listing filter dimensions. It is efficiently structured, though for a tool of this complexity (14 params), it is lean enough that some information is sacrificed.

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 14-parameter tool with only 29% schema coverage, no output schema, and a nested features object, the description is not sufficient on its own. It omits pagination semantics (offset/limit), sorting behavior, and the structure of the features filter. The description is an adequate high-level summary, but an agent needs to inspect the schema carefully to invoke all capabilities correctly, and several params remain undocumented in both schema and description.

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?

With only 29% schema description coverage, the description partially compensates: 'budget' maps to min_price/max_price, 'type' to room_type, 'university' to university_id, 'campus' to campus_id, 'distance' to max_distance_km, and 'features' to the features object — all of which lack schema descriptions. However, it leaves limit, offset, order_by, and other params semantically unexplained, and does not clarify that the features parameter is a nested filter object.

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 uses a specific verb ('Search'), a clear resource ('approved and available student rooms'), and enumerates the key filter dimensions (budget, type, university, campus, distance, features). The 'approved and available' qualifier adds useful scope beyond the tool name. However, it does not explicitly differentiate from siblings like get_room_details, compare_rooms, or rank_room_matches, though the resource type inherently sets it apart from search_cities and search_universities.

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?

The description implies this is the tool for filtering student rooms by criteria, which is enough to infer basic usage. It does not explicitly state when to prefer alternatives (e.g., get_room_details for a single room, compare_rooms for side-by-side comparison) or mention exclusions. The absence of required parameters suggests unconstrained search is possible, but this is not stated.

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