Vector Toolbox MCP

pinecone_rerank

Rerank retrieved candidate documents with a hosted cross-encoder to reorder results by query relevance, refining broad search results into top matches.

Instructions

Rerank a candidate list with a hosted cross-encoder.

Use it as a second stage: retrieve widely with pinecone_search (top_k 50-100), then rerank down to the handful you actually want.

Args: documents: [{"id": "d1", "text": "..."}]. rank_fields: Which field the reranker reads, default ["text"].

Input Schema

TableJSON Schema

Name	Required	Default
`model`	No	bge-reranker-v2-m3
`query`	Yes
`top_n`	No
`documents`	Yes
`rank_fields`	No
`return_documents`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 13, 2026

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description carries the burden. It discloses the hosted nature of the cross-encoder and its role as a re-scoring stage, which is useful context beyond the structured fields, but says nothing about cost, latency, or behavior on malformed/missing documents.

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?

Front-loads purpose then usage in two tight sentences, followed by a short Args block. The Args block only covers two of six parameters, so it is slightly unbalanced, but no sentence is wasted.

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?

An output schema exists so return values need not be described. However, with no annotations and four undocumented parameters (notably top_n and return_documents), the description is not complete enough for an agent to call this correctly without guessing.

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 description coverage is 0%, so the description must compensate. It documents the documents shape ({"id", "text"}) and rank_fields default, but leaves model, top_n (how many to keep), query, and return_documents unexplained — a meaningful gap for a 6-param tool.

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 (rerank) and resource (candidate list), plus the mechanism (hosted cross-encoder). It also names the sibling it complements (pinecone_search), so an agent can place it in the pipeline without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly prescribes when to use it: as a second stage after retrieving widely with pinecone_search (top_k 50-100), then reranking down to a handful. Both the alternative and the selecting condition are stated, leaving nothing to inference.

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