discover_rooms

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

With no annotations provided, the description carries full burden. It discloses key behaviors: fetches reservations across a broad time window, saves the catalogue locally to a specific path (with config override), and requires user input if no locations are given. It does not explicitly state read-only status but implies no destructive action beyond local file saving.

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?

Every sentence in the three-paragraph description earns its place: first paragraph states purpose, second explains process and outcome, third handles missing input. It is front-loaded and free of extraneous information.

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 covers purpose, process, file output, configuration overrides, impact on sibling tool (search_rooms), and missing input handling. With an output schema present (context signal), it does not need to explain return values. The description is fully adequate for this tool's complexity.

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?

The input schema provides 100% coverage with descriptions for both parameters. The description adds value by explaining configuration fallback for 'locations' (INDICO_*_ROOM_LOCATIONS) and default behavior for 'instance' (server default), and the third paragraph explains the overall usage pattern, enriching beyond schema.

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 starts with a specific verb+resource: 'Scan reservation history to build a room catalogue and save it locally.' It explains the process (fetches reservations across 2 years + 6 months, discovers rooms, saves to file) and distinguishes itself from sibling tools like search_rooms and book_room by positioning it as a prerequisite for search_rooms to work without a location argument.

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 explicitly states that after running this tool, search_rooms works without needing a location argument, implying this tool should be used before search_rooms. It also provides guidance for missing input: 'If no locations are provided and none are configured, ask the user for the site/location names...' but does not explicitly list when not to use it or alternative approaches.

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