snapp-mcp

Overview Schema Source Related Servers Discussions Admin

Find location

find_location

Read-onlyIdempotent

Convert a place name or address into latitude and longitude, using optional city-center coordinates to bias results for location lookup.

Instructions

Turn a place name or address into latitude/longitude.

Biased toward near_lat/near_long (default Tehran): pass a city center for other cities.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "find_location"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max places.
`query`	Yes	Place or landmark, e.g. 'میدان ونک'.
`near_lat`	No	Bias latitude, e.g. a city center.
`near_long`	No	Bias longitude.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.4.0Nov 7, 2026

changedInput schema / properties / limit / description

Previous value: -"Max places to return."New value: +"Max places."

removedInput schema / properties / near_lat / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

changedInput schema / properties / near_lat / description

Previous value: -"Bias latitude (e.g. a city center from list_cities)."New value: +"Bias latitude, e.g. a city center."

addedInput schema / properties / near_lat / type
```
Added value: +[
+  "number",
+  "null"
+]
```

removedInput schema / properties / near_long / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / near_long / type
```
Added value: +[
+  "number",
+  "null"
+]
```

changedInput schema / properties / query / description

Previous value: -"Place, street or landmark, e.g. 'میدان ونک'."New value: +"Place or landmark, e.g. 'میدان ونک'."

Changed9 schema fields changedv0.2.0Oct 17, 2026

removedInput schema / properties / limit / title
```
Removed value: -"Limit"
```

changedInput schema / properties / near_lat / description

Previous value: -"Bias results toward this latitude (e.g. a city center from list_cities)."New value: +"Bias latitude (e.g. a city center from list_cities)."

removedInput schema / properties / near_lat / title
```
Removed value: -"Near Lat"
```

changedInput schema / properties / near_long / description

Previous value: -"Bias results toward this longitude."New value: +"Bias longitude."

removedInput schema / properties / near_long / title
```
Removed value: -"Near Long"
```

changedInput schema / properties / query / description

Previous value: -"Place, street, landmark or neighbourhood, Persian works best, e.g. 'میدان ونک'."New value: +"Place, street or landmark, e.g. 'میدان ونک'."

removedInput schema / properties / query / title
```
Removed value: -"Query"
```

removedInput schema / title

Removed value: -"find_locationArguments"

changedOutput schema / (root)

Previous value: -{
-  "additionalProperties": true,
-  "title": "find_locationDictOutput",
-  "type": "object"
-}New value: +null

First observedv0.1.1Oct 2, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds a genuinely behavioral detail the annotations and schema do not: results are geo-biased and default to Tehran when no near coordinates are given. It says nothing about no-match handling, ranking, or how limit interacts with bias.

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

Conciseness5/5

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

Two short lines, front-loaded with the core transformation and then the non-obvious bias caveat. Every clause carries information; there is no filler.

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 four documented parameters, no output schema and rich annotations, the definition covers input semantics and the important default-geography behavior. It stops short of describing what a returned place looks like or whether multiple ranked matches come back, but the output schema's absence limits how much is required.

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 goes beyond it by explaining that near_lat/near_long act as a bias rather than a hard filter, that the bias exists even when they are null (Tehran), and by advising a city center for other cities. That meaning is not derivable from the schema's 'Bias latitude' wording alone.

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

Purpose5/5

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

The description states a concrete transformation ('place name or address into latitude/longitude'), which is a specific verb+resource and implicitly separates this forward geocoder from the reverse_geocode sibling. An agent can classify the tool without opening the schema.

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 clear operational guidance: results are biased toward near_lat/near_long, the bias defaults to Tehran, and callers should pass a city center for other cities. It does not explicitly compare to reverse_geocode or state when not to use it, keeping it short of a 5.

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