Lviv Public Transport

Search Stops

search_stops

Read-onlyIdempotent

Finds stops by name (Ukrainian or English transliteration, case-insensitive, partial match) and returns each stop's numeric ID, coordinates, and the routes serving it. Use this as the first step when the user names a stop or landmark stop (e.g. "Опера", "Rynok", "Головний вокзал") and you need a stop ID for get_stop_realtime or find_routes_between. One name usually covers both sides of the street under different IDs; each is returned, and the routes list tells them apart. Use get_stops_around_location instead when you have coordinates rather than a name.

Input Schema

Name	Required	Description	Default
`limit`	No	Maximum stops to return (1–25, default 10).
`query`	Yes	Stop name or part of it, e.g. "Ринок", "opera", "Стрийська".

Output Schema

Name	Required	Description	Default
`data`	Yes
`view`	Yes
`ui_blocks`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 4, 2026
- removedOutput schema / properties / ui_blocks / items / properties / data / properties / center / additionalItems
```
Removed value: -false
```
- changedOutput schema / properties / ui_blocks / items / properties / data / properties / center / items
```
Previous value: -[
-  {
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  {
-    "type": [
-      "number",
-      "null"
-    ]
-  }
-]New value: +false
```
- addedOutput schema / properties / ui_blocks / items / properties / data / properties / center / prefixItems
```
Added value: +[
+  {
+    "type": [
+      "number",
+      "null"
+    ]
+  },
+  {
+    "type": [
+      "number",
+      "null"
+    ]
+  }
+]
```
Changed8 schema fields changedNov 2, 2026
- removedInput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
- removedOutput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
- removedOutput schema / additionalProperties
```
Removed value: -false
```
- removedOutput schema / properties / data / additionalProperties
```
Removed value: -false
```
- removedOutput schema / properties / data / properties / stops / items / additionalProperties
```
Removed value: -false
```
- removedOutput schema / properties / ui_blocks / items / additionalProperties
```
Removed value: -false
```
- removedOutput schema / properties / ui_blocks / items / properties / data / additionalProperties
```
Removed value: -false
```
- removedOutput schema / properties / ui_blocks / items / properties / data / properties / layers / additionalProperties
```
Removed value: -false
```
AddedSep 23, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), so the description focuses on behavior: matching is case-insensitive and partial, and a single name can legitimately return multiple IDs for both sides of the street, with the routes list as the disambiguator. That is genuinely useful non-obvious behavior. It stops short of describing empty-result behavior or how limit truncation is signalled, which keeps it off a 5.

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?

Front-loaded with purpose and return shape, then usage, then the alternative — a sensible ordering with no filler sentences. It is slightly longer than needed, since the inline examples ("Опера", "Rynok") partially duplicate the schema's own query examples, and the bold markup is decorative rather than structural.

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 two-parameter read tool with full schema coverage, an output schema, and annotations covering safety, the description covers essentially everything an agent needs to select and call it. The only minor gap is behavior at the boundaries — no hits, or hitting the limit cap — which is neither in the description nor the schema.

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, but the description adds real meaning beyond the schema by declaring the query accept Ukrainian or English transliteration and that matching is case-insensitive and partial — semantics the schema's plain "Stop name or part of it" does not convey. The limit parameter is left entirely to the schema, preventing a higher score.

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 opens with a specific verb+resource ("Finds stops by name") and immediately states the return payload: numeric ID, coordinates, and serving routes. It distinguishes itself from sibling get_stops_around_location by input type (name vs. coordinates), so an agent can route without opening either schema.

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?

Explicitly positions itself as the "first step" when the user names a stop, and names the two downstream consumers of the returned ID (get_stop_realtime, find_routes_between). It also states the exclusion condition: use get_stops_around_location when you have coordinates rather than a name.

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

All Lviv Public Transport 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.