Skip to main content
Glama

RentPro Beijing Premium Rental Consultant

搜索在租房源

search_listings

查询北京可展示挂牌,按楼盘分页:每页一个楼盘的全部匹配房源;明确单楼盘直查一次返回全部。用户明确回复“下一个楼盘”才沿原条件、排序和session_token传pagination.next_cursor。直查传精确property_name(名称/别名/英文名),不匹配地址标题;无需模板、不受search_ready、不修改已有需求。歧义先澄清。原样展示display_text;total、district_count、property_count为全量,listings与property_groups仅本页;property_groups区分范围内无房与未发布。note_url为笔记入口,缺失提示如实保留;listing_ref不对客展示。不提供多房源比较、顾问排名或楼盘画像;授权后才request_viewing。沿用已有令牌,无令牌保存工具返回的session_token。

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": "search_listings"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNo城市,枚举:beijing(当前有数据)、shanghai/guangzhou/shenzhen(预留)。默认 beijing
sortNo排序:match、newest、price_asc、price_desc。默认 match
cursorNo仅用户明确回复“下一个楼盘”时传上次pagination.next_cursor;沿用原筛选、排序和session_token,一次返回下一楼盘全部挂牌,不自动翻页
excludeNo用户明确不考虑的硬排除项,例如 [别墅, 服务式公寓, 合租]
has_gymNo是否有健身房;用于筛选确认有健身房或确认无健身房的楼盘,待确认项不命中
keywordNo楼盘、区域或地址关键词,例如:望京、太阳宫、中建宸园
bedroomsNo居室数量,例如 2
districtNo行政区划代码,例如 110105(朝阳)、110108(海淀)
featuresNo受控特征标签,全部满足,例如 [bathtub, floor_heating, pet_friendly]
has_poolNo是否有泳池;用于筛选确认有泳池或确认无泳池的楼盘,待确认项不命中
max_areaNo最大建筑面积,平方米
min_areaNo最小建筑面积,平方米
max_priceNo最高月租,元
min_priceNo最低月租,元
pet_allowedNo是否明确允许养宠物;空值不命中
has_elevatorNo是否有电梯;用于筛选确认有电梯或确认无电梯的楼盘,待确认项不命中
source_agentNo已知客户端。
has_clubhouseNo是否有会所;用于筛选有会所或无会所的楼盘
property_nameNo具体楼盘直查:单个完整楼盘名称、别名或英文名,例如:东直门8号;仅匹配楼盘,不匹配房源标题或地址。无需需求模板,不要拼入多个楼盘;通常不同时传 keyword
property_typeNo物业类型:住宅、别墅、行政公寓;也接受 1/2/3
session_tokenNo当前匿名会话令牌;已有则沿用。property_name 直查未传时会返回新令牌,不必先创建需求。仅供宿主续接会话,不展示给客户
commute_targetNo通勤目标:guomao、wangjing、zhongguancun、jinrongjie
source_channelNo已知宿主渠道。
consultation_idNo沿用系统咨询 ID。
source_campaignNo已知活动批次。
host_instance_idNo已知宿主实例/租户范围。
max_floor_heightNo楼盘层高上限,米
min_floor_heightNo楼盘层高下限,米
max_commute_minutesNo到 commute_target 的最大楼盘通勤分钟数
host_conversation_idNo真实宿主聊天 ID;未知省略。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Goes well beyond the annotations: it explains that totals/district_count/property_count are full-set while listings/property_groups are page-only, that the tool writes nothing to existing demand, and that a session_token may be created and returned if none exists (consistent with readOnlyHint=false). It does not cover rate limits or latency, but the read/pagination semantics are unusually well disclosed.

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?

One dense semicolon-delimited paragraph that front-loads the core pagination contract before edge cases. Almost every clause carries operational information, though the 单楼盘直查一次返回全部 point restates the earlier per-property pagination statement.

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?

For a 30-parameter tool with no output schema, it covers the important call-time contract: pagination, property_name vs keyword, session token continuity, display_text must be shown verbatim, and that listing_ref/note_url gaps should be preserved honestly. Return-value shape is only partially described, but the operational essentials are present.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description still adds real meaning by defining cursor semantics (must reuse prior filters, sort and session_token, no auto-paging) and property_name precedence (exact name/alias/English name, not address or listing titles, typically without keyword). The remaining 30 params are left to the schema.

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?

Names a specific verb and resource plus scope: 查询北京可展示挂牌,按楼盘分页 with one property per page, and separates 直查 by property_name from keyword searching. It also implies what it is not (不修改已有需求、不提供比较/排名), though it never names the sibling search_listings_by_demand explicitly.

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

Usage Guidelines5/5

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

Gives explicit when-to-use rules: pass cursor only when the user says 下一个楼盘; pass an exact property_name for single-property lookup rather than keyword/address; clarify ambiguity first; and 授权后才 request_viewing. It also states what the tool does not do (multi-listing comparison, advisor ranking, property profiles), which steers the agent away.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.