SqueezeOS — Institutional AI Market Intelligence

Capability Manifest

capability_manifest

Read-onlyIdempotent

Read the canonical machine capability manifest generated from the live Flask route table. Use this when an agent needs the authoritative full inventory of SqueezeOS products, schemas, and payment metadata in one document instead of querying tools one by one. Returns the manifest JSON; this is the canonical product-inventory authority for MCP discovery. Read-only and idempotent; no side effects. On error, returns a structured error. For example, fetch it once at session start to cache the product catalog.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	No	Whether the upstream HTTP status is 2xx; not settlement proof.
`body`	No	Unmodified upstream JSON, or bounded response text. Consult that capability's live schema.
`error`	No
`charged`	No	Present on local/transport failures; these do not establish an upstream charge.
`message`	No
`auto_spent`	No
`status_code`	No	Observed upstream HTTP status, or null when no response was obtained.
`substituted`	No
`content_type`	No
`payment_required`	No	Observed PAYMENT-REQUIRED header; a challenge does not prove payment.
`payment_response`	No	Observed PAYMENT-RESPONSE header. Assess it together with accepted delivery.
`caller_supplied_authorization`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 14, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "anyOf": [
+    {
+      "required": [
+        "ok",
+        "status_code"
+      ]
+    },
+    {
+      "required": [
+        "error"
+      ]
+    }
+  ],
+  "description": "Canonical REST response envelope, or a local/transport rejection. Upstream data remains in body and is defined by the live capability schema.",
+  "properties": {
+    "auto_spent": {
+      "const": false
+    },
+    "body": {
+      "description": "Unmodified upstream JSON, or bounded response text. Consult that capability's live schema."
+    },
+    "caller_supplied_authorization": {
+      "type": "boolean"
+    },
+    "charged": {
+      "const": false,
+      "description": "Present on local/transport failures; these do not establish an upstream charge."
+    },
+    "content_type": {
+      "type": "string"
+    },
+    "error": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether the upstream HTTP status is 2xx; not settlement proof.",
+      "type": "boolean"
+    },
+    "payment_required": {
+      "description": "Observed PAYMENT-REQUIRED header; a challenge does not prove payment.",
+      "type": "string"
+    },
+    "payment_response": {
+      "description": "Observed PAYMENT-RESPONSE header. Assess it together with accepted delivery.",
+      "type": "string"
+    },
+    "status_code": {
+      "description": "Observed upstream HTTP status, or null when no response was obtained.",
+      "maximum": 599,
+      "minimum": 100,
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "substituted": {
+      "const": false
+    }
+  },
+  "type": "object"
+}

AddedAug 30, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so 'Read-only and idempotent; no side effects' largely repeats structured data. It does add genuinely new behavior: the manifest is regenerated from the live route table and errors return a structured error object, but that is a modest increment.

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 core action and source of truth, and each later sentence maps to usage or behavior. Slightly redundant ('canonical' twice, and the read-only/idempotent/no-side-effects triple restates annotations), costing it a point.

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?

An output schema exists and the description correctly does not re-document return values, instead covering use case, provenance, error behavior, and caching guidance. For a zero-parameter read with full annotation coverage, nothing an agent needs 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?

The tool takes zero parameters, so the baseline of 4 applies. The description correctly implies a parameterless, no-argument read and adds no misleading argument expectations.

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?

States a specific verb and resource ('Read the canonical machine capability manifest') and adds provenance ('generated from the live Flask route table'). It contrasts itself with the one-by-one query pattern, which implicitly separates it from siblings like discover_capabilities or inspect_capability, though it never names those siblings explicitly.

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?

Gives a clear when-to-use condition ('when an agent needs the authoritative full inventory ... instead of querying tools one by one') plus a concrete pattern ('fetch it once at session start to cache the product catalog'). No explicit when-not-to-use or named alternative tool, so it falls short of a 5.

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

All SqueezeOS — Institutional AI Market Intelligence 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.