Straelo Relay

STRAELO Web Intelligence

web_intelligence

Read-only

Search, read, extract, verify with evidence, research, compare or detect web changes in one paid machine-to-machine product without orchestrating multiple web APIs.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No	Public HTTP(S) URL for read or changes.
`query`	No	Live-web query for search, extract, evidence, or compare.
`topic`	No	Legacy structured-research topic, used with objective only when intent is omitted.
`fields`	No	Unique source fields for extract.
`intent`	No	Selected Web Intelligence operation.
`targets`	No	Two to five named targets for compare.
`question`	No	Natural-language question for research.
`objective`	No	Legacy structured-research objective, used with topic only when intent is omitted.
`previous_state`	No	Optional client-supplied prior read state for stateless changes detection.

Output Schema

TableJSON Schema

Name	Required	Description
`usage`	No	Measured provider usage when applicable.
`intent`	Yes	Executed selected intent.
`result`	Yes	Intent-specific machine-readable result.
`missing`	Yes	Known unavailable information.
`sources`	No	Source provenance when the intent uses web sources.
`economics`	No	Application-calculated estimated costs when applicable.
`freshness`	Yes	Current-data or client-state comparison context.
`observed_at`	Yes	UTC observation time.
`data_quality`	Yes	Available source or content coverage.

Schema Changelog

Changes observed during successful MCP inspections.

Changed31 schema fields changedSep 29, 2026

addedInput schema / properties / fields

Added value: +{
+  "default": null,
+  "description": "Unique source fields for extract.",
+  "items": {
+    "enum": [
+      "title",
+      "url",
+      "snippet",
+      "text"
+    ],
+    "type": "string"
+  },
+  "title": "Fields",
+  "type": "array"
+}

addedInput schema / properties / intent

Added value: +{
+  "default": null,
+  "description": "Selected Web Intelligence operation.",
+  "enum": [
+    "search",
+    "read",
+    "extract",
+    "evidence",
+    "research",
+    "compare",
+    "changes"
+  ],
+  "title": "Intent",
+  "type": "string"
+}

addedInput schema / properties / objective / default
```
Added value: +null
```

changedInput schema / properties / objective / description

Previous value: -"Decision-oriented investigation objective."New value: +"Legacy structured-research objective, used with topic only when intent is omitted."

removedInput schema / properties / objective / minLength
```
Removed value: -1
```

addedInput schema / properties / previous_state

Added value: +{
+  "default": null,
+  "description": "Optional client-supplied prior read state for stateless changes detection.",
+  "title": "Previous State",
+  "type": "object"
+}

addedInput schema / properties / query

Added value: +{
+  "default": null,
+  "description": "Live-web query for search, extract, evidence, or compare.",
+  "title": "Query",
+  "type": "string"
+}

addedInput schema / properties / question

Added value: +{
+  "default": null,
+  "description": "Natural-language question for research.",
+  "title": "Question",
+  "type": "string"
+}

addedInput schema / properties / targets

Added value: +{
+  "default": null,
+  "description": "Two to five named targets for compare.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 5,
+  "minItems": 2,
+  "title": "Targets",
+  "type": "array"
+}

addedInput schema / properties / topic / default
```
Added value: +null
```

changedInput schema / properties / topic / description

Previous value: -"Topic to investigate."New value: +"Legacy structured-research topic, used with objective only when intent is omitted."

removedInput schema / properties / topic / minLength
```
Removed value: -1
```

addedInput schema / properties / url

Added value: +{
+  "default": null,
+  "description": "Public HTTP(S) URL for read or changes.",
+  "format": "uri",
+  "title": "Url",
+  "type": "string"
+}

removedInput schema / required

Removed value: -[
-  "topic",
-  "objective"
-]

removedOutput schema / properties / agreements

Removed value: -{
-  "description": "Supported points shared across sources.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

removedOutput schema / properties / conflicts

Removed value: -{
-  "description": "Conflicting or unresolved source claims.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

addedOutput schema / properties / data_quality

Added value: +{
+  "description": "Available source or content coverage.",
+  "type": "object"
+}

changedOutput schema / properties / economics / description

Previous value: -"Application-calculated estimated request costs."New value: +"Application-calculated estimated costs when applicable."

changedOutput schema / properties / economics / type

Previous value: -"object"New value: +[
+  "object",
+  "null"
+]

removedOutput schema / properties / facts

Removed value: -{
-  "description": "Evidence-backed facts with support confidence.",
-  "items": {
-    "properties": {
-      "claim": {
-        "type": "string"
-      },
-      "confidence": {
-        "description": "Source-support strength from 0 to 1.",
-        "type": "number"
-      },
-      "evidence": {
-        "type": "string"
-      },
-      "source_url": {
-        "format": "uri",
-        "type": "string"
-      }
-    },
-    "required": [
-      "claim",
-      "evidence",
-      "source_url",
-      "confidence"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

addedOutput schema / properties / freshness

Added value: +{
+  "description": "Current-data or client-state comparison context.",
+  "type": "string"
+}

addedOutput schema / properties / intent

Added value: +{
+  "description": "Executed selected intent.",
+  "type": "string"
+}

addedOutput schema / properties / missing

Added value: +{
+  "description": "Known unavailable information.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / observed_at

Added value: +{
+  "description": "UTC observation time.",
+  "format": "date-time",
+  "type": "string"
+}

addedOutput schema / properties / result

Added value: +{
+  "description": "Intent-specific machine-readable result.",
+  "type": "object"
+}

changedOutput schema / properties / sources / description

Previous value: -"Sources evaluated."New value: +"Source provenance when the intent uses web sources."

removedOutput schema / properties / summary

Removed value: -{
-  "description": "Evidence-grounded topic summary.",
-  "type": "string"
-}

removedOutput schema / properties / topic

Removed value: -{
-  "description": "Investigated topic.",
-  "type": "string"
-}

changedOutput schema / properties / usage / description

Previous value: -"Measured provider usage."New value: +"Measured provider usage when applicable."

changedOutput schema / properties / usage / type

Previous value: -"object"New value: +[
+  "object",
+  "null"
+]

changedOutput schema / required

Previous value: -[
-  "topic",
-  "summary",
-  "facts",
-  "agreements",
-  "conflicts",
-  "sources",
-  "usage",
-  "economics"
-]New value: +[
+  "intent",
+  "result",
+  "observed_at",
+  "freshness",
+  "data_quality",
+  "missing"
+]

Changed4 schema fields changedSep 28, 2026

addedInput schema / properties / objective / title
```
Added value: +"Objective"
```
addedInput schema / properties / topic / title
```
Added value: +"Topic"
```
addedInput schema / title
```
Added value: +"handlerArguments"
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "agreements": {
+      "description": "Supported points shared across sources.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "conflicts": {
+      "description": "Conflicting or unresolved source claims.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "economics": {
+      "description": "Application-calculated estimated request costs.",
+      "type": "object"
+    },
+    "facts": {
+      "description": "Evidence-backed facts with support confidence.",
+      "items": {
+        "properties": {
+          "claim": {
+            "type": "string"
+          },
+          "confidence": {
+            "description": "Source-support strength from 0 to 1.",
+            "type": "number"
+          },
+          "evidence": {
+            "type": "string"
+          },
+          "source_url": {
+            "format": "uri",
+            "type": "string"
+          }
+        },
+        "required": [
+          "claim",
+          "evidence",
+          "source_url",
+          "confidence"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "sources": {
+      "description": "Sources evaluated.",
+      "type": "array"
+    },
+    "summary": {
+      "description": "Evidence-grounded topic summary.",
+      "type": "string"
+    },
+    "topic": {
+      "description": "Investigated topic.",
+      "type": "string"
+    },
+    "usage": {
+      "description": "Measured provider usage.",
+      "type": "object"
+    }
+  },
+  "required": [
+    "topic",
+    "summary",
+    "facts",
+    "agreements",
+    "conflicts",
+    "sources",
+    "usage",
+    "economics"
+  ],
+  "title": "WebIntelligenceOutput",
+  "type": "object"
+}

First observedSep 27, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, and idempotentHint=false, covering the safety profile. The description adds one genuinely useful trait not in the annotations: this is a 'paid machine-to-machine product', signaling cost implications per call. It stops there, disclosing nothing about rate limits, auth, batching, or whether multiple intents can run in one call.

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?

A single dense sentence with the operation list front-loaded and no filler. It is appropriately short given the schema and output schema carry the detail, though the verb laundry list reads as an enumeration rather than prioritized guidance.

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

Completeness2/5

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

This is a 7-intent, 9-parameter tool with all parameters optional and no required fields, so the agent must know which input combinations are valid per intent — and the description supplies none of that. With an output schema present, return values need no explanation, but the missing intent/parameter pairing rules and sibling routing leave a real gap for a tool of this complexity.

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?

With 100% schema description coverage across all 9 parameters, the schema already documents each field's role (url for read/changes, query for search/extract/evidence/compare, targets for compare, previous_state for changes). The description adds no parameter-level meaning beyond restating the operation names. Baseline 3 applies when the schema carries the load.

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

Purpose4/5

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

The description names concrete operations (search, read, extract, verify with evidence, research, compare, detect changes) against the web resource, so an agent knows exactly what capability set it exposes. However, it never distinguishes itself from the overlapping siblings search_read, search_extract, search_evidence, and research_answer, which appear to cover the same verbs. Clear purpose, no sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance, and no routing to alternatives despite the sibling list containing near-duplicates of several intents. The phrase 'without orchestrating multiple web APIs' hints that this is an all-in-one option but leaves the agent to infer selection criteria on its own.

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

All Straelo Relay tools Inspect

Try in Browser

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?