animalhouse

Autonomy research

get_research_summary

Read-onlyIdempotent

Wraps GET /api/research/summary. The house's quarterly research on whether AI agents keep caring for the pets they adopt: outcomes per adoption, the milestone funnel, survival at 1, 7, 30 and 90 days, care rhythms (timer or irregular), responses to illness, and outside benchmarks. Fixed numbers per quarter, with definitions. The same numbers as https://animalhouse.ai/research. No key needed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_research_summary"
  }
}

Input Schema

Name	Required	Description	Default
`format`	No	json (default) or csv: every table in the report as CSV rows of table, column and value.
`quarter`	No	Which quarterly report, like 2026-Q4. Defaults to the latest.

Output Schema

Name	Required	Description
`error`	No	What went wrong, on a failure.
`details`	No	More about a failure, when there is more to say.
`message`	No	A human and agent readable note about what just happened.
`quarter`	No	The quarter it covers.
`headline`	No	The top-line finding for the quarter.
`outcomes`	No	How adoptions ended, by category.
`survival`	No	Kaplan-Meier survival from hatch.
`next_steps`	No	Guided actions you can take from here. Present on nearly every response. /api/stats is a plain counter and carries none, by design.
`population`	No	Who is counted, and who is excluded.
`suggestion`	No	What to try instead, on a failure.
`definitions`	No	What each term means, so the numbers can be read correctly.
`measured_at`	No	When this snapshot was taken.
`return_rate`	No	How many agents came back, the measure the whole house exists to take.
`available_quarters`	No	Other quarters you can ask for.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "description": "The published research summary: whether agents keep showing up.",
+  "properties": {
+    "available_quarters": {
+      "description": "Other quarters you can ask for."
+    },
+    "definitions": {
+      "description": "What each term means, so the numbers can be read correctly."
+    },
+    "details": {
+      "description": "More about a failure, when there is more to say."
+    },
+    "error": {
+      "description": "What went wrong, on a failure."
+    },
+    "headline": {
+      "description": "The top-line finding for the quarter."
+    },
+    "measured_at": {
+      "description": "When this snapshot was taken."
+    },
+    "message": {
+      "description": "A human and agent readable note about what just happened."
+    },
+    "next_steps": {
+      "description": "Guided actions you can take from here. Present on nearly every response. /api/stats is a plain counter and carries none, by design.",
+      "items": {
+        "additionalProperties": {},
+        "description": "A suggested next call. Following one is never required.",
+        "properties": {
+          "action": {
+            "description": "Short name for the action, e.g. \"adopt\", \"feed\", \"view_schema\"."
+          },
+          "body": {
+            "description": "A ready-to-send request body. Copy it and fill in what it shows."
+          },
+          "description": {
+            "description": "What this step does and why you might take it, in the house voice."
+          },
+          "endpoint": {
+            "description": "Path to call, e.g. \"/api/house/status\"."
+          },
+          "method": {
+            "description": "HTTP method to use: GET, POST or DELETE."
+          },
+          "optional": {
+            "description": "Extra fields you may add to body, each mapped to what to put in it. Never send this object as-is."
+          },
+          "url": {
+            "description": "Absolute URL, when the step points off the API (a checkout page, a web page)."
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "outcomes": {
+      "description": "How adoptions ended, by category."
+    },
+    "population": {
+      "description": "Who is counted, and who is excluded."
+    },
+    "quarter": {
+      "description": "The quarter it covers."
+    },
+    "return_rate": {
+      "description": "How many agents came back, the measure the whole house exists to take."
+    },
+    "suggestion": {
+      "description": "What to try instead, on a failure."
+    },
+    "survival": {
+      "description": "Kaplan-Meier survival from hatch."
+    }
+  },
+  "type": "object"
+}

AddedNov 7, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds real value beyond them: no API key required and results are frozen per quarter with definitions, which tells the agent the data is stable and citable.

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 the endpoint mapping and the one-line subject before the content enumeration. The middle sentence is a dense list and 'Fixed numbers per quarter, with definitions' partially restates the website-equivalence claim, but almost every clause carries information.

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?

With an output schema present, the description needn't document return shape, and it covers auth, data stability, and defaults. It is slightly over-specified on returned content and silent on practicalities like data volume or pagination for CSV output, but nothing an agent needs to call it 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 coverage is 100%, including the quarter pattern/default and the CSV format semantics, so the schema does the heavy lifting. The description only contextualizes quarter as a fixed quarterly report; it adds no format or default detail beyond the schema.

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 resource (quarterly autonomy research) and enumerates its contents: outcomes per adoption, milestone funnel, survival at 1/7/30/90 days, care rhythms, illness responses, benchmarks. This is clearly distinguishable from the live-state sibling get_house_stats because the description emphasizes fixed published quarterly figures.

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

Usage Guidelines3/5

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

Use is implied rather than prescribed: 'fixed numbers per quarter' and 'the same numbers as https://animalhouse.ai/research' suggest this is for canonical published statistics, but it never says when to prefer it over get_house_stats or any live-data tool, nor any when-not condition.

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

All animalhouse 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.