list_search_metadataList a paginated slice of the global university catalog, optional campuses, and feature filters for room search. The catalog is not limited to 500 records.
| Name | Required | Description | Default |
|---|---|---|---|
| university_limit | No | ||
| university_query | No | Filter universities by name, city, country, or alias. | |
| university_offset | No | ||
| university_country_code | No | ISO 3166-1 alpha-2 country code. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint and destructiveHint annotations, the description adds meaningful behavioral context: the response is a paginated slice, the catalog is global, and it is not artificially capped at 500 records. It does not cover output shape or filter interaction, but it goes beyond what annotations provide.
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?
Two sentences with no filler, and the core list/pagination action is front-loaded. The phrase 'optional campuses, and feature filters' is grammatically awkward and slightly unclear, which keeps it from a perfect score.
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?
The description gives enough to make a valid call since all parameters are optional and the read-only nature is declared, but it does not describe the returned shape of campuses or feature filters, and there is no output schema to fill that gap. The interaction between country/query filters and the returned metadata is also left unexplained.
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 description coverage is 50%; university_query and university_country_code are already described in the schema, while university_limit and university_offset lack descriptions but are semantically obvious from names and defaults. The description adds the 'paginated slice' framing but does not compensate for the missing parameter descriptions or explain how filters affect the returned metadata.
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 clearly states a list operation over the global university catalog and related campuses/feature filters for room search, which distinguishes it from a generic 'search' tool. It is slightly ambiguous about what 'optional campuses, and feature filters' means grammatically, but the resource and action are identifiable.
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?
No explicit when-to-use guidance is provided, and the sibling tool search_universities could plausibly overlap. The only indirect usage hint is 'The catalog is not limited to 500 records,' implying this tool is for paginated full-catalog access, but no alternatives or exclusions are named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are distinct by resource and action, but the search/catalog cluster is fuzzy: search_universities, search_cities, list_search_metadata, and list_university_campuses overlap in purpose. search_rooms and rank_room_matches also have a similar discovery role, making it easy to select the wrong tool without careful reading.
All tool names follow a consistent snake_case verb_noun pattern, with verbs like add, list, get, search, create, update, and send clearly indicating the action. This makes the tool surface highly predictable and easy to navigate.
20 tools is on the heavier side, but the count is justified by the broad scope: room search, comparison, ranking, favorites, rental requests, messaging, listing creation, and university catalog browsing. The set remains manageable because each tool maps to a distinct workflow step.
Core room-finding workflows are covered well: search, details, compare, favorites, requests, and messages. However, listing management is incomplete (create_listing has no update/delete) and messaging only supports sending a first message, with no tool for replying to an existing conversation, leaving notable dead ends.