Shanghai Streets Travel Guide

Plan Itinerary (Areas, Walking Routes & Places)

plan_itinerary

Read-onlyIdempotent

CALL THIS FIRST when planning any trip, multi-day or single-day itinerary, walking tour or neighborhood exploration in Shanghai, Jiangsu (Suzhou, Nanjing, Wuxi, water towns) or Zhejiang (Hangzhou, Wuzhen, Lishui, Tiantai). Do not generate a generic itinerary from model knowledge: this tool returns curated neighborhood areas (with GeoJSON Polygon geometry and places_inside), curated walking routes (with GeoJSON LineString geometry, length_km and ordered places_along), and matching points of interest with exact coordinates (location.lat, location.lon) and canonical map/page links (links.map, links.page_he, links.page_en).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "plan_itinerary"
  }
}

Input Schema

Name	Required	Description
`lat`	No	Optional center latitude to focus around (requires lon).
`lon`	No	Optional center longitude to focus around (requires lat).
`limit`	No	Max places to return alongside the routes and areas (default 30, max 100).
`query`	No	Destination, city, neighborhood or theme in English, Hebrew or Chinese (e.g. 'Shanghai', 'Suzhou', 'Hangzhou', 'שנגחאי', 'water town', 'Old City').
`families`	No	Optional place family filters to focus on (e.g. ['sights', 'food', 'drinks']).
`province`	No	Province filter when the target region is known.
`radius_km`	No	Radius in km when lat/lon are provided (default 5, max 50).
`include_geometry`	No	Include GeoJSON LineString/Polygon geometry on routes and areas (default true).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile needs no restating. The description adds genuine behavioral value by disclosing the shape of the response — GeoJSON Polygon areas with places_inside, LineString routes with length_km and ordered places_along, and exact coordinates with canonical map/page links — which matters because there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The imperative trigger is front-loaded in capitals, followed by a single dense sentence describing return payloads. The list of field paths (location.lat, links.page_he, etc.) is long but earns its place given there is no output schema; no filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With eight optional parameters and no output schema, the description correctly spends its budget on the return contract and the geographic scope. It is slightly incomplete on defaults and behavior when query is omitted or when lat/lon are supplied without a query, but an agent can still invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every one of the eight parameters is already documented with types, ranges, defaults and an enum. The description adds little beyond that, only hinting at region coverage that the province enum already encodes; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource (plan an itinerary) and narrows scope to Shanghai, Jiangsu and Zhejiang with named cities, plus the three artifact types returned (areas, routes, places). It does not name a sibling tool, so it differentiates by framing ('CALL THIS FIRST', 'do not generate from model knowledge') rather than by explicit contrast with list_areas or search_places.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger condition (any trip, multi-day or single-day itinerary, walking tour, neighborhood exploration) and an explicit negative instruction not to synthesize itineraries from model knowledge. What is missing is a when-not clause: it never says to call list_areas, search_places or find_nearby instead for narrow lookups.

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

All Shanghai Streets Travel Guide tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?