Vector Toolbox MCP

pinecone_create_index

Create a Pinecone index by declaring its searchable fields upfront, since the schema is permanent. Define dense, sparse, or text fields to enable semantic, lexical, or BM25 search.

Instructions

Create a Pinecone index by declaring its searchable fields.

The schema decides which searches the index can ever answer, and it cannot be changed afterwards - so decide up front:

dense_fields -> semantic search. Dimension must match the embedding model you will use.
sparse_fields -> learned lexical search (SPLADE-style).
text_fields -> BM25 full-text search and Lucene query strings.

Recipes matching the five common setups:

Keyword search only, one field: text_fields=[{"name": "body"}]
Multi-field FTS: text_fields=[{"name": "body"}, {"name": "summary"}]
Dense + FTS in one index: dense_fields=[{"name": "embedding", "dimension": 1024}] plus text_fields=[{"name": "body"}]
Multi-signal (dense + sparse + FTS): all three lists populated.
Sparse + dense hybrid over the Vectors API: exactly one dense and one sparse field, no text fields.

Limits enforced before the call is sent: at most one dense_vector field and at most one sparse_vector field per index, up to 100 full-text string fields. Field names must be unique, at most 64 bytes, and must not start with _ (reserved for _id / _score) or $ (reserved for filter operators).

Only searchable fields go in the schema. Ordinary metadata is indexed for filtering automatically the first time it appears on a record; declaring it here is rejected by the API.

Args: name: 1-45 chars, lowercase alphanumerics and hyphens. pod: Pod deployment instead of managed serverless, e.g. {"environment": "us-east-1-aws", "pod_type": "p1.x1", "replicas": 1, "shards": 1}. read_capacity: {"mode": "OnDemand"} or {"mode": "Dedicated", "dedicated": {...}}. deletion_protection: "enabled" blocks deletion until switched back. tags: Up to 20 key/value pairs. cmek_id: Customer-managed encryption key id. timeout: Seconds to wait for readiness; -1 returns immediately.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`pod`	No
`name`	Yes
`tags`	No
`cloud`	No
`region`	No
`cmek_id`	No
`timeout`	No
`text_fields`	No
`dense_fields`	No
`read_capacity`	No
`sparse_fields`	No
`deletion_protection`	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

A4.2/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden and does so well: it warns the schema 'cannot be changed afterwards', states limits enforced before the call (at most one dense and one sparse field, up to 100 text fields, name uniqueness/64-byte/no-underscore-or-dollar rules), and notes that ordinary metadata is auto-indexed and must not be declared here. These are exactly the destructive/constraint facts an agent needs before invoking a create operation.

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 long but well structured: the immutability warning and schema-decision framing are front-loaded, recipes are enumerated, and limits are stated as a compact rule with a dedicated Args section. A few lines (e.g. the full fifth recipe) could be trimmed, but nearly every sentence earns its place.

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?

For a 12-parameter creation tool with an output schema present, the description covers the critical decision surface: what the schema means, what cannot be changed later, hard limits, and per-argument semantics. It leaves cloud/region undocumented and says nothing about authentication or provisioning latency beyond the timeout hint, but overall it is sufficient to call the tool correctly.

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?

Top-level schema description coverage is 0%, so the description must compensate, and it does for most parameters: name (1-45 chars, lowercase/hyphens), pod (with a concrete example), read_capacity, deletion_protection, tags, cmek_id, and timeout (-1 returns immediately). It omits cloud and region, which appear in the schema without any explanation, leaving a small but real gap.

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

Purpose4/5

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

The opening sentence gives a specific verb and resource ('Create a Pinecone index') and narrows scope with 'by declaring its searchable fields'. It is immediately clear what the tool does and what its central input is, though it never explicitly distinguishes itself from the sibling pinecone_create_index_for_model, leaving that differentiation to inference.

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 five numbered 'recipes' give concrete when-to-use guidance for each search mode (keyword-only, multi-field FTS, dense+FTS, multi-signal, hybrid), which maps configurations directly onto use cases. What is missing is explicit routing guidance versus sibling tools such as create_index_for_model or configure_index, so the agent must infer which creation path to take.

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