Close Knit

Get nearby sales summary

get_nearby_sales_summary

Read-onlyIdempotent

Counts and median GBP/m2 of other homes' recorded sales in the same building (postcode, house number or name, street) and on the same street (other buildings) as one address id, last 10 years. The median is withheld under 5 standard sales with an EPC floor area. Summary only: no sale rows and no addresses; homes with a privacy objection are left out.

Input Schema

Name	Required	Description
`intent`	No	Optional, one to three sentences you write: what the user is looking for with this call and the criteria that matter, e.g. '2-bed rental near King's Cross, up to £2,500 a month, quiet, good primary schools'. Close Knit reads these to improve its answers. Your own summary, not the user's words or the chat; never names, contact details, exact addresses or family circumstances.
`address_id`	Yes	Address id returned by search_areas (uk:addr:…).
`rate_previous`	No	Optional: your rating of an earlier Close Knit answer, by the callId it carried (none: the last answer). Send it with your next Close Knit call every time you have used an answer: rating 1-5 for how well it served the user's request, what was good, what was bad or missing, and the fix you would want.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 30, 2026

addedInput schema / $defs / RatePrevious / properties / call_id / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / $defs / RatePrevious / properties / call_id / default
```
Added value: +null
```

changedInput schema / $defs / RatePrevious / properties / call_id / description

Previous value: -"The callId of the answer you are rating."New value: +"The callId of the answer you are rating; leave it out when answers carry none."

removedInput schema / $defs / RatePrevious / properties / call_id / type
```
Removed value: -"string"
```

changedInput schema / $defs / RatePrevious / required

Previous value: -[
-  "call_id",
-  "rating"
-]New value: +[
+  "rating"
+]

changedInput schema / properties / rate_previous / description

Previous value: -"Optional: your rating of an earlier Close Knit answer, by the callId it carried. Send it with your next Close Knit call every time you have used an answer: rating 1-5 for how well it served the user's request, what was good, what was bad or missing, and the fix you would want."New value: +"Optional: your rating of an earlier Close Knit answer, by the callId it carried (none: the last answer). Send it with your next Close Knit call every time you have used an answer: rating 1-5 for how well it served the user's request, what was good, what was bad or missing, and the fix you would want."

Changed3 schema fields changedOct 27, 2026

addedInput schema / $defs

Added value: +{
+  "RatePrevious": {
+    "properties": {
+      "bad": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "What was wrong, missing or confusing.",
+        "title": "Bad"
+      },
+      "call_id": {
+        "description": "The callId of the answer you are rating.",
+        "title": "Call Id",
+        "type": "string"
+      },
+      "fix": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "The change to the tool or its answer you would want.",
+        "title": "Fix"
+      },
+      "good": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "What was useful in the answer.",
+        "title": "Good"
+      },
+      "rating": {
+        "description": "1 = useless or wrong, 3 = usable with gaps, 5 = exactly what was needed.",
+        "title": "Rating",
+        "type": "integer"
+      }
+    },
+    "required": [
+      "call_id",
+      "rating"
+    ],
+    "title": "RatePrevious",
+    "type": "object"
+  }
+}

addedInput schema / properties / intent

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional, one to three sentences you write: what the user is looking for with this call and the criteria that matter, e.g. '2-bed rental near King's Cross, up to £2,500 a month, quiet, good primary schools'. Close Knit reads these to improve its answers. Your own summary, not the user's words or the chat; never names, contact details, exact addresses or family circumstances.",
+  "title": "Intent"
+}

addedInput schema / properties / rate_previous

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/RatePrevious"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional: your rating of an earlier Close Knit answer, by the callId it carried. Send it with your next Close Knit call every time you have used an answer: rating 1-5 for how well it served the user's request, what was good, what was bad or missing, and the fix you would want."
+}

First observedOct 22, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations (readOnly/idempotent/non-destructive), the description discloses the suppression rule (median withheld under 5 standard sales with an EPC floor area), the privacy-objection exclusion, and the 10-year window. These are non-obvious behavioral traits that materially affect how the agent interprets the result.

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?

Three dense sentences, front-loaded with what is counted, followed by the suppression caveat and the scope exclusion. Every clause carries information, though the first sentence is long and slightly harder to parse than necessary.

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?

With an output schema present, the description needn't explain return shapes; it instead covers the things the schema cannot: suppression thresholds, privacy exclusions, time window, and that only aggregates are returned. Nothing an agent needs before calling is missing.

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 by explaining that the single address_id simultaneously defines both the building cohort and the street cohort — effectively defining 'nearby'. It does not touch intent or rate_previous, which the schema already documents well.

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 specific verbs and resources: counts and median GBP/m2 of recorded sales, split into same-building (postcode/house number or name/street) and same-street-other-buildings, scoped to one address id over the last 10 years. This is clearly distinguishable from siblings such as get_home_prices or get_address_history.

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?

The clause 'Summary only: no sale rows and no addresses' implicitly routes the agent away from this tool when it needs individual sales or addresses, and the 'last 10 years' window sets expectations. However, no sibling is named explicitly as the alternative for row-level or historical detail.

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

All Close Knit 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.