Skip to main content
Glama

LiquiLens Failure Radar

Historical diagnostic: one Indian case replay

evidence_institution
Read-onlyIdempotent

A sourced Indian construction-PIT quarterly replay, lens alert timing and hit/miss/false-alarm verdict. Slugs from evidence_india. Filing-availability proxies do not establish a validated backtest.

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": {
      "slug": "<slug>"
    },
    "name": "evidence_institution"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYeskebab-case replay slug, e.g. 'dhfl'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / slug / description
      Previous value: -"kebab-case slug of a replayed institution, e.g. 'dhfl' or 'global-trust-bank'"New value: +"kebab-case replay slug, e.g. 'dhfl'"
  2. First observed

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, so the safety profile is covered. The description adds one piece of genuine behavioral context — that filing-availability proxies mean results are not a validated backtest — which usefully sets expectations about reliability. It still says nothing about what the replay returns or how verdicts are derived.

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?

Two short sentences with no filler, and the subject of the tool is front-loaded. The telegraphic, multi-clause phrasing ('lens alert timing and hit/miss/false-alarm verdict') trades clarity for density, costing it a point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one well-documented parameter, no output schema, and strong annotations, the structured data carries most of the load. Still, a diagnostic tool whose whole value is a verdict should say more about what the replay produces and what the timing/verdict fields mean.

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 coverage is 100% for the single required slug parameter, including format guidance and an example ('dhfl'), so the baseline is 3. The description's only addition is provenance ('Slugs from evidence_india'), which slightly helps an agent source a valid value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource ('Indian construction-PIT quarterly replay') and the core output ('lens alert timing and hit/miss/false-alarm verdict'), but dense jargon like 'construction-PIT' and 'lens' is left unexplained, so an agent cannot fully predict what the replay does. It hints at adjacency to evidence_india but doesn't clearly differentiate from siblings like failure_radar_institution or institution_evidence_monitor.

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?

'Slugs from evidence_india' implies a useful prerequisite: get the slug from evidence_india first, which is real routing guidance. However, there is no explicit statement of when to choose this versus failure_radar_institution or institution_evidence_monitor, and no when-not-to-use condition beyond the caveat that proxies don't establish a validated backtest.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.