Skip to main content
Glama
Sign In
HullForge MCP Connector

HullForge MCP Connector

by jigwright
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Read

hf_read
Read-onlyIdempotent

Run read-only HullForge tools such as describe, list, get, find, and audit. Arguments are validated against the tool's schema and no changes are made.

Instructions

Call a HullForge tool that only reads: describe, list, get, find, audit. Changes nothing. Arguments are checked against the tool's schema first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tool": "<tool>"
    },
    "name": "hf_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNoThe tool's arguments, matching the schema hf_tool_schema returned.
toolYesThe tool's exact name, as hf_search_tools returned it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

The annotations already declare readOnlyHint, idempotentHint and destructiveHint, so 'changes nothing' adds no new information. The one genuinely new behavioral fact is that arguments are validated against the tool's schema first, but the failure mode (error vs. correction), latency, and return shape are not described.

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 short front-loaded sentences with the read-only constraint first and the validation caveat last. Slight redundancy between 'only reads' and 'Changes nothing', and the naming convention for tools could be stated instead of a bare verb list, but there is no filler.

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?

As a generic dispatcher with a nested args object it needs to convey scope, which it does. There is no output schema, so the description ideally would say something about what gets returned (the wrapped tool's result), but the schema's 100% coverage of the two parameters plus the annotations cover most of what an agent needs to invoke it.

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 description coverage is 100% and both parameters (tool, args) are already explained in the schema, including that args must match what hf_tool_schema returned and that tool must be the exact name from hf_search_tools. The description adds no semantics beyond that, so the baseline 3 applies.

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 action (call a HullForge tool) and constrains it to the read side, backed by an enumeration of qualifying families (describe, list, get, find, audit) that an agent can match a target tool against. The contrast with the mutating sibling hf_write is clear through 'only reads / changes nothing', though hf_write is never named.

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?

Usage is only implied: the read-only framing tells the agent this is for non-mutating calls, but there is no explicit 'use hf_write for mutations' routing, no statement about what to do if the named tool isn't read-only, and no instruction to call hf_search_tools/hf_tool_schema first (only the schema properties hint at that ordering).

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

Deploy Server

Other Tools