Skip to main content
Glama
quality-screener

Quality Screener MCP Server

by quality-screener
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

screen_share

Idempotent

Generate a shareable link for a custom quality scoring screen. Recipients can view and load the exact configuration, and identical configs return the same URL without duplication.

Instructions

Create a shareable link for a screen (CustomScoreConfig) and return its URL.

Persists the screen configuration and returns a short, public link that can be copy-pasted to anyone — recipients open it to view and load the exact screen. The link is content-addressed: sharing an identical config returns the same URL instead of creating a duplicate.

Args: config: The complete CustomScoreConfig to share — weighted metric groups, scoring parameters (winsorizePercentile, missingDataPercentile, normalizeGroupZScores, includeDuplicatesInScoring), and an optional nested filters block. Loose inputs (snake_case keys, legacy winsorize/zScore flags, or top-level filter keys) are normalized to this shape so the shared link always renders.

Returns: dict with url (the shareable link to copy-paste), slug (the short identifier), created (True if newly created, False if an identical screen already existed), and view_count.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
configYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, the description discloses that this persists configuration, is content-addressed so identical configs return the same URL, and creates no duplicate when the screen already exists. It also explains input normalization behavior, giving agents a concrete model of side effects without contradicting idempotentHint or readOnlyHint.

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?

The description is well-structured with a one-sentence summary, a behavior section, and explicit Args/Returns sections. Every sentence adds meaningful operational detail; the most important behavior—link creation and content addressing—appears early.

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?

Given an absent output schema and a single complex nested parameter, the description covers input semantics, normalization, return keys (url, slug, created, view_count), persistence, and deduplication. Nothing needed for correct invocation or interpreting the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the config parameter is an opaque object with additionalProperties allowed. The description compensates fully by enumerating the key fields (groups, winsorizePercentile, missingDataPercentile, normalizeGroupZScores, includeDuplicatesInScoring, optional filters) and clarifying loose-input normalization.

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 states a specific verb and resource: 'Create a shareable link for a screen (CustomScoreConfig) and return its URL.' It clearly differentiates itself from siblings that list, compute, or manage systems by focusing on sharing a screen configuration via a persistent link.

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 intended use is clear: generate a shareable, public link that can be copy-pasted to anyone so they can view and load an exact screen. It does not explicitly name alternatives or list when-not-to-use, but the description's scoping makes the usage context obvious among the sibling tools.

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