Skip to main content
Glama

LiquiLens — the Failure Radar

by io.github.beepboop2025

Historical diagnostic: US construction-PIT watchlist

evidence_us
Read-onlyIdempotent

Read the US bank current-amended-vintage diagnostic: every FDIC-insured bank scored quarterly from free call-report data, replayed against all 552 receivership failures since 2008 — recall 72.8% at a 21.7-month median lead, AUC 0.854. Includes the marquee replays (SVB, Signature, First Republic, both 2026 catches), the fraud-driven miss kept in full view, and the seven named 2023-2026 misses, published the week they failed; the 2026 scoreboard reads 2 of 4 flagged a year early. Read the semantics before quoting: the flag is a budgeted watchlist (top decile per quarter), not an institution-level verdict, so report the budget beside the recall and the misses beside the hits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
include_trajectoriesNoalso return per-quarter score series for the marquee replays (large payload); default false

TDQS

A4.1/5.0
Behavior5/5

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

The description goes well beyond the read-only/idempotent annotations by disclosing the watchlist is budgeted (top decile), not an institution-level verdict, and explicitly notes the inclusion of misses (e.g., fraud-driven miss, seven named misses) to avoid misinterpretation. This provides crucial behavioral context.

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?

The description is dense but each sentence adds value: purpose, performance metrics, included replays/misses, and semantic caveat. It is front-loaded with the main verb and resource, though the statistical details could be trimmed without losing core guidance.

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 no output schema, the description explains what content to expect (scores, replays, misses, scoreboard) and the semantic caveat. It lacks explicit return format but is otherwise sufficient for a read-only diagnostic tool.

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?

The only parameter, include_trajectories, is fully documented in the schema with default and description. The tool description adds no extra parameter context, but schema coverage is 100%, so the baseline of 3 applies.

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?

The description clearly states the tool reads a specific diagnostic ('US bank current-amended-vintage diagnostic') and describes its content: every FDIC-insured bank scored quarterly, replayed against 552 failures with performance metrics. It distinguishes from sibling tools via 'US' and 'historical diagnostic' in the title and description.

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?

The description implies usage when one needs the US bank watchlist diagnostic, but it does not explicitly mention when not to use or alternatives. There is guidance on interpretation ('Read the semantics before quoting') but no direct comparison to sibling tools.

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

All LiquiLens — the Failure Radar 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

A4.4/5.0
Disambiguation5/5

Each tool targets a distinct resource, sector, or function: sector-specific boards (corporate, household, crypto, stablecoin, failure radar), evidence details by region, verification, search, and review packet generation. Descriptions explicitly delineate boundaries, leaving no ambiguity about which tool to select.

Naming Consistency3/5

There are recognizable families (e.g., *_board for dashboards, evidence_* for validation records), but the set mixes conventions: noun-phrase boards, verb-first tools like universe_search and verify_published_record, and standalone nouns like forward_odds. This is readable but not uniform.

Tool Count4/5

17 tools is slightly above the ideal 3-15 range, but each tool has a distinct purpose and no redundancy. The count feels justified given the breadth of domains (India, US, Europe, crypto, stablecoins) and functions (monitoring, validation, verification, review).

Completeness5/5

The set covers the full workflow: universe_search for discovery, sector boards for monitoring, failure_radar_institution for deep dives, evidence_* for validation, forward_odds for probability context, verify_published_record for integrity, and institution_review_packet for human review. No obvious gaps or dead ends for the stated failure-radar domain.

Resources