最快的用法：把用户的原话直接传进来（如“这附近有什么好吃的”“闺蜜聚餐去哪”“哪家烧烤好吃又有性价比”）， near 填用户所在城市、区或地点（如“北京中关村”），有坐标可填 lat/lng（WGS84）。 返回 text（可直接转述的中文答案）、understood（如何理解这句话）和 items（店铺明细）。 need=location 时表示需要先问用户在哪里。
| Name | Required | Description | Default |
|---|---|---|---|
| lat | No | ||
| lng | No | ||
| city | No | ||
| near | No | ||
| question | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does a decent job: it discloses the three return fields (text/understood/items) and the special need=location outcome that requires a follow-up question. It stops short of covering failure modes, permissions, or rate limits, but the sentinel-value disclosure is genuinely useful behavioral context.
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 front-loaded with the fastest usage pattern and example phrasings, then parameter guidance, then the return shape. The examples and inline instructions are dense but each sentence carries actionable information, with no obvious filler.
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?
For a 5-parameter, no-output-schema, no-annotation tool, the description covers the core calling path and even documents return values since no output schema exists. The main gap is the unexplained city parameter and the absence of any sibling-tool disambiguation.
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 coverage is 0%, so the description must compensate, and it largely does: it explains question (pass raw user words, with examples), near (city/district/place), and lat/lng (WGS84 coordinate format). The separate city parameter is never addressed, leaving one of five params undocumented in both schema and description.
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 makes clear this is a natural-language restaurant query tool: pass the user's own words and get back an answer, an understanding, and shop details (text/understood/items). It is specific about inputs and outputs, but never contrasts itself with the sibling search_restaurants, so an agent must infer which to pick.
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?
It gives concrete when-to-use guidance: pass the user's original phrasing directly, fill near with city/district/place, and use lat/lng when coordinates exist. It also explains the need=location sentinel that tells the agent to ask the user for their location. No explicit when-not-to-use or alternative-tool routing is offered.
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.