Nearest restroom, exit, and food for a specific point — a room code (floor-specific, e.g. the exact nearest bathroom to SH-217), a building name, or GPS coordinates {lat, lon}. Returns specific named venues ranked by distance.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | No | Latitude (e.g. from device GPS) — pair with lon | |
| lon | No | Longitude — pair with lat | |
| location | No | Room code or building name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and open-world behavior. The description adds that results are specific named venues ranked by distance, and provides an example with floor-specific room codes. This goes beyond the annotations by detailing the output structure and input specificity. No contradictions.
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?
The description is extremely concise: two sentences that immediately state the purpose, list possible inputs, and describe the output. Every word is necessary. No filler or repetition. It is front-loaded with the core action ('Nearest...').
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 what the tool does, inputs, and outputs (ranked venues). However, it does not specify if multiple results are returned or the format of the data. Given no output schema, a bit more detail on return structure would be helpful, but it is still adequate for a simple lookup tool.
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 already describes each parameter (lat, lon, location). The description adds meaning by clarifying that 'location' can be a room code or building name, and that lat/lon are a pair for GPS coordinates. It also gives a concrete example (SH-217). This fully compensates for the 100% schema coverage, adding usage context.
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 it returns nearest restroom, exit, and food for a given point. It specifies three input types (room code, building name, GPS coordinates) and mentions ranking by distance. This distinguishes it from siblings like 'find_room' which locates a specific room, and 'accessible_route' which provides routes.
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 usage when needing nearby facilities but does not explicitly state when to avoid this tool or provide alternatives among siblings. For example, it could mention using 'accessible_route' for routing or 'find_room' for locating a specific room. The guidance is clear but lacks exclusions.
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.
Each tool has a clearly distinct purpose: accessibility routes, general routes, access checks, room finding, nearby amenities, operational overview, day planning, prohibited items, and readiness check. No overlap or ambiguity.
All tool names use lowercase snake_case and are descriptive. While most follow a verb_noun pattern (e.g., check_access, find_room), a few are noun-only (nearby, overview), but the overall pattern is consistent and predictable.
9 tools is well within the ideal range for a domain-specific server. Each tool serves a necessary function without redundancy, and the count feels appropriate for the Capitol complex navigation and visitor support domain.
The tool set covers core domains: navigation, accessibility, room lookup, amenities, security restrictions, and day planning. Minor gaps like event scheduling or tour information exist, but the essential use cases are well-covered.