Skip to main content
Glama
devopam

MCPg - Production-grade PostgreSQL MCP Server

Analyze reranker lift

analyze_reranker_lift
Read-only

Measure correlation between bi-encoder and cross-encoder ranks to determine if your reranker is actively reordering. Low correlation indicates real reordering; high correlation means it confirms the bi-encoder order.

Instructions

Per-query Spearman + Kendall correlation between bi-encoder and cross-encoder ranks, aggregated across queries in the window. Low correlation = the reranker is actively reordering (doing real work); high correlation = the reranker mostly confirms the bi-encoder order. Optional model / retrieval_index filters. Surfaces reranker_idle (WARNING) when the reranker rarely changes ordering. Reads from mcpg_rag.rerank_events; returns a report with zero counts when the table doesn't exist or the window is empty.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNo
modelNo
databaseNoOptional: target a configured secondary (read-only) database by name; omit for the primary. Call list_databases to see the configured ids.
retrieval_indexNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelYes
findingsYes
query_countYes
window_daysYes
mean_kendallYes
p25_spearmanYes
p75_spearmanYes
mean_spearmanYes
interpretationYes
retrieval_indexYes
Behavior5/5

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

Discloses data source (mcpg_rag.rerank_events) and edge cases (zero counts when table missing or window empty). No contradiction with annotations (readOnlyHint=true).

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?

Three sentences, front-loaded with the core metric, efficient wording, no redundancy.

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 output schema exists, annotations present, and parameters explained, the description covers behavior, edge cases, and data source adequately.

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?

Schema coverage is only 25% (only database has description), but description adds meaning for model and retrieval_index filters and implies days default. It partially compensates for low coverage.

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?

Description clearly states the core function: computing per-query Spearman and Kendall correlations between bi-encoder and cross-encoder ranks. It also mentions a specific alert (reranker_idle), making the tool's purpose precise and distinguishable.

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?

Description provides interpretation guidance (low correlation = active reordering, high = confirming) and mentions optional filters. However, it does not explicitly compare to sibling tools like analyze_rerank_ndcg or state when not to use this tool.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/devopam/MCPg'

If you have feedback or need assistance with the MCP directory API, please join our Discord server