Teardrop

Web Search

web_search

Read-only

Real-time web search via Tavily for current events, fact-checking, and research. Use search_depth='advanced' for complex queries (higher quality, higher cost) and topic='news' or 'finance' for headlines or market information.

Use when: Choose when the task needs current, external, or factual information not available from on-chain or local data — e.g. news, prices, documentation, or fact-checking.

Limitations: Returns web snippets, not raw page bodies; results depend on Tavily coverage. Advanced depth costs more. Not a substitute for on-chain tools like get_token_price.

Alternatives: get_token_price, http_fetch

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	Search query
`topic`	No	Search topic: 'general' for web, 'news' for headlines, 'finance' for markets	general
`num_results`	No	Number of web search results to return (1–20, default 5).
`search_depth`	No	'basic' for fast results, 'advanced' for thorough research (higher cost)	basic

Output Schema

TableJSON Schema

Name	Required	Description	Default
`note`	No
`query`	Yes
`results`	Yes
`num_results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedAug 14, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
addedInput schema / properties / num_results / title
```
Added value: +"Num Results"
```
addedInput schema / properties / query / title
```
Added value: +"Query"
```
addedInput schema / properties / search_depth / title
```
Added value: +"Search Depth"
```
addedInput schema / properties / topic / title
```
Added value: +"Topic"
```
addedInput schema / title
```
Added value: +"mcp_web_searchArguments"
```

addedOutput schema / $defs

Added value: +{
+  "SearchResult": {
+    "properties": {
+      "score": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Score"
+      },
+      "snippet": {
+        "title": "Snippet",
+        "type": "string"
+      },
+      "title": {
+        "title": "Title",
+        "type": "string"
+      },
+      "url": {
+        "title": "Url",
+        "type": "string"
+      }
+    },
+    "required": [
+      "title",
+      "url",
+      "snippet"
+    ],
+    "title": "SearchResult",
+    "type": "object"
+  }
+}

addedOutput schema / properties / results / items / $ref
```
Added value: +"#/$defs/SearchResult"
```

removedOutput schema / properties / results / items / properties

Removed value: -{
-  "score": {
-    "anyOf": [
-      {
-        "type": "number"
-      },
-      {
-        "type": "null"
-      }
-    ],
-    "default": null,
-    "title": "Score"
-  },
-  "snippet": {
-    "title": "Snippet",
-    "type": "string"
-  },
-  "title": {
-    "title": "Title",
-    "type": "string"
-  },
-  "url": {
-    "title": "Url",
-    "type": "string"
-  }
-}

removedOutput schema / properties / results / items / required
```
Removed value: -[
-  "title",
-  "url",
-  "snippet"
-]
```
removedOutput schema / properties / results / items / title
```
Removed value: -"SearchResult"
```
removedOutput schema / properties / results / items / type
```
Removed value: -"object"
```

First observedJul 9, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations declare readOnlyHint=true, and the description adds beyond this by disclosing that the tool returns web snippets rather than raw page bodies, that results depend on Tavily coverage, that advanced depth increases cost, and that it should not replace on-chain tools. These behavioral details are not redundant with the annotation.

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?

The description is organized into clear purpose, use-when, limitations, and alternatives paragraphs, allowing an agent to parse key decisions quickly. Every sentence earns its place, and the most important information about what the tool does is front-loaded.

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?

For a simple search tool with an output schema and a read-only annotation, the description covers all relevant decision factors: purpose, use cases, limitations, cost implications, and alternatives. Nothing needed to select or invoke the tool correctly is missing.

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 description coverage is 100%, so the schema already fully documents all four parameters. The description adds a marginal selection rule for using search_depth='advanced' on complex queries and topic='news' or 'finance' for headlines or market information, but this largely restates the schema's own descriptions, so no significant semantic value is added.

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?

States a specific verb and resource: real-time web search via Tavily for current events, fact-checking, and research. It clearly differentiates from sibling on-chain and utility tools by emphasizing external, current information, and explicitly says it is not a substitute for get_token_price.

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?

Provides an explicit 'Use when' section naming the conditions for selection: current, external, factual information not available from on-chain or local data, with concrete examples like news, prices, documentation, and fact-checking. It also names alternatives (get_token_price, http_fetch) and states limitations, giving the agent clear routing guidance.

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

All Teardrop 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?