Skip to main content
Glama

SqueezeOS — Institutional AI Market Intelligence

by io.github.Timwal78

Call Capability

call_capability

Call a concrete SqueezeOS REST path on the canonical public host. GET is read-only. POST requires confirm_write=true. If the target returns 402 and no payment_signature was supplied, this tool preserves PAYMENT-REQUIRED and returns the closest no-spend SML alternative from the Capability Router. Retry the original route only with a challenge-specific payment_signature. Sensitive operator/control routes and arbitrary auth headers are not exposed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNo
pathYesConcrete SqueezeOS path beginning with /; do not pass a full URL.
queryNo
methodYes
confirm_writeNo
payment_signatureNoCanonical x402 v2 PAYMENT-SIGNATURE value bound to this exact target-resource challenge.
alternative_intentNoOptional natural-language intent used to rank the closest SML alternative after an unsigned HTTP 402.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / properties / alternative_intent
      Added value: +{
+  "description": "Optional natural-language intent used to rank the closest SML alternative after an unsigned HTTP 402.",
+  "maxLength": 500,
+  "minLength": 1,
+  "type": "string"
+}
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

The description carries the safety burden since annotations are open-ended: it discloses write gating, the 402 fallback behavior, and the payment-signature retry rule. It also explicitly states the access boundary for sensitive routes and auth headers.

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?

Four sentences, front-loaded with the core action, with no filler. Every sentence contributes operative detail: read/wrote semantics, fallback, retry, and access restrictions.

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?

Covers the main input rules, 402 handling, retry policy, and exclusions, enabling safe invocation. A modest gap remains because there is no explicit normal success-return format or non-402 error behavior, and no output schema exists.

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?

Adds meaning beyond schema for method, confirm_write, payment_signature, and alternative_intent. Schema covers path/payment_signature/alternative_intent, but body and query remain undocumented; still the critical invocation flow is clarified.

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 action ('Call'), resource ('concrete SqueezeOS REST path'), and host ('canonical public host'), with clear scoping that sensitive operator/control routes are not exposed. This distinguishes it from sibling discovery/manifest tools as the execution tool.

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 clear context: GET is read-only, POST requieres confirm_write=true, and 402 without payment_signature triggers an SML fallback with rety only on challenge-specific signature. It implies the selection vs siblings but doesn't explicitly name alternatives like discover_capabilities.

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools have clear boundaries: discover searches, inspect examines one, compare contrasts, recommend interprets natural language, and call executes. Some ambiguity exists between capability_manifest and discover_capabilities for inventory listing, and recommend_capability could be confused with discover_capabilities, but descriptions generally prevent misselection.

Naming Consistency4/5

All names are lowercase snake_case, and the core capability operations follow a verb_noun pattern. The noun-led capability_manifest, system_status, and x402_* resources deviate from that pattern, and capability names mix singular and plural, but the naming remains readable and internally consistent per subdomain.

Tool Count5/5

Ten tools is well within the ideal range and each tool maps to a distinct part of the capability discovery, comparison, payment, and execution workflow. There are no obviously redundant or throwaway tools, so the count feels appropriately scoped.

Completeness5/5

The set covers the full read-only market-intelligence lifecycle: inventory, search, inspect, compare, recommend, call, payment readiness, contract lookup, and settlement evidence. Operator CRUD is explicitly outside scope, so there are no meaningful dead ends for an agent using this surface.

Resources