patient-services

search

Read-only

Searches the clinic, doctor, treatment, service and policy entity index by name, alias, or summary text. Queries work in English, Turkish, German, Arabic, Russian, French and Polish. Each result carries an id that can be passed directly to the fetch tool.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	Restrict results to one entity kind. Omit to search every kind.
`query`	Yes	Free-text search query in any of the seven site languages, e.g. "dental implant price", "implant fiyatı", "Zahnimplantat Preis", "цена импланта"
`top_k`	No	Maximum number of results to return (default 10, maximum 50). Results are ordered by relevance, so the first rows are the strongest matches. total_matches reports how many entities matched in total.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes
`meta`	Yes
`evidence`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedAug 17, 2026

addedInput schema / properties / kind

Added value: +{
+  "description": "Restrict results to one entity kind. Omit to search every kind.",
+  "enum": [
+    "clinic",
+    "doctor",
+    "treatment",
+    "credential",
+    "service",
+    "policy"
+  ],
+  "type": "string"
+}

changedInput schema / properties / query / description

Previous value: -"Free-text search query, e.g. a doctor name, treatment name, or clinic name"New value: +"Free-text search query in any of the seven site languages, e.g. \"dental implant price\", \"implant fiyatı\", \"Zahnimplantat Preis\", \"цена импланта\""

addedInput schema / properties / top_k

Added value: +{
+  "description": "Maximum number of results to return (default 10, maximum 50). Results are ordered by relevance, so the first rows are the strongest matches. total_matches reports how many entities matched in total.",
+  "maximum": 50,
+  "minimum": 1,
+  "type": "integer"
+}

addedOutput schema / properties / data / properties / results / items / properties / id
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / data / properties / results / items / properties / title
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / data / properties / results / items / properties / url
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / properties / data / properties / results / items / required

Previous value: -[
-  "entity_id",
-  "kind",
-  "name",
-  "canonical_url",
-  "summary"
-]New value: +[
+  "id",
+  "title",
+  "url",
+  "entity_id",
+  "kind",
+  "name",
+  "canonical_url",
+  "summary"
+]

addedOutput schema / properties / data / properties / returned
```
Added value: +{
+  "type": "integer"
+}
```

addedOutput schema / properties / data / properties / total_matches

Added value: +{
+  "description": "How many entities matched before top_k truncation.",
+  "type": "integer"
+}

addedOutput schema / properties / data / properties / truncated

Added value: +{
+  "description": "True when total_matches exceeded top_k and results were cut.",
+  "type": "boolean"
+}

changedOutput schema / properties / data / required

Previous value: -[
-  "results"
-]New value: +[
+  "results",
+  "total_matches",
+  "returned",
+  "truncated"
+]

First observedAug 13, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, so the description adds useful context by specifying the entity index scope and supported languages. No contradictions with annotations. It does not cover rate limits or pagination, but those are not necessary given the annotations and 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.

Conciseness5/5

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

Two tight sentences that front-load the action and include only essential information: entity types, search fields, languages, and the id-to-fetch linkage. No filler.

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

Completeness5/5

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

Given an output schema exists and annotations handle safety, the description fully covers the search scope, language support, and follow-up workflow. No major gaps for an agent to understand how to invoke this tool.

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 coverage is 100% for all three parameters, so the baseline is 3. The description does not add parameter-specific semantics beyond the schema; it mentions the search scope and languages but no extra syntax, defaults, or examples beyond what schema already provides.

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?

Clearly states it searches the clinic, doctor, treatment, service, and policy entity index by name, alias, or summary text. This distinguishes it from sibling getter tools like get_clinic_profile and get_prices by being the search entry point.

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?

Explicitly explains that results carry an id that can be passed to the fetch tool, implying a search-then-fetch workflow. It does not explicitly mention when not to use this tool versus get_* tools, but the intended workflow is clear.

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

All patient-services 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?