Fabrica (Sepolia testnet)

What needs my attention on Fabrica

what_needs_attention

Read-onlyIdempotent

One ranked list of everything waiting on the connected person on Fabrica (Sepolia Testnet): loans past or near maturity and offers waiting on their properties first, then steps of properties they are adding that wait on them, then fees to approve and dollars (USDC) in their accounts ready to cash out, then checks on their live properties (property taxes, owner contact, recovery status) and removals in progress. Each item has its kind, property, title, why, due date when known, the link where it is done and who acts. Fees and checks cover up to 20 live properties per call. checked lists what was read, so an empty list means nothing was found there. Reads only; uses the portfolio:read and onramp:read grants and skips what the connection lacks.

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": "what_needs_attention"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 2, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, and the description adds substantial behavior beyond them: the ranking order of categories, a per-call cap ('fees and checks cover up to 20 live properties'), the permission grants used, and the fact that missing grants cause silent skipping. It also explains the return semantics of 'checked' and what an empty list means, which is exactly the kind of context annotations cannot carry.

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?

It is front-loaded with the core definition and every sentence carries information (ordering, item fields, caps, grants, empty-list semantics). It loses a point for being a single very dense run-on enumeration that would scan better as a short ordered list, but there is no filler.

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?

There is no output schema, and the description compensates fully by naming the fields of each returned item (kind, property, title, why, due date, link, who acts) and explaining the 'checked' companion list. For a zero-parameter aggregate read tool, an agent has everything needed to call it and interpret the result.

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 there is nothing for the description to disambiguate; baseline for a zero-param tool applies. The description does not waste space restating an empty 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 verb and resource: a single ranked aggregate list of everything waiting on the connected person, and enumerates the categories it covers (maturity/offers, adding steps, fees/USDC, property checks, removals). That enumeration makes it clearly distinguishable from single-domain siblings such as get_my_loans, get_my_offers, or get_my_properties_being_added.

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 description conveys clear usage context: it is a read-only attention/dashboard entry point that aggregates across domains, and it discloses prerequisite scopes (read:loans, read:onramp) plus graceful degradation ('skips what the person cannot access'). What it does not do is explicitly route the caller — it never says to prefer this over the individual sibling listers when a single domain is needed, so alternatives are implied rather than stated.

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

All Fabrica (Sepolia testnet) 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.