Skip to main content
Glama

Build the semantic search index

zotero_index

Build and manage a local hybrid-search index for your Zotero library, enabling fast keyword and vector search. Start a background build, then poll status until done.

Instructions

Manage the local hybrid-search index used by zotero_semantic_search. The build runs as a background job on the server, so this tool returns immediately — never blocks on large libraries. action: "build" (or "refresh") starts a background build: it pages the library's top-level items (100-at-a-time, capped at 5000 items unless a smaller limit is given), indexes their text (title, abstract, creators, tags) for BM25 keyword search and — if an embedding provider is configured — vector search, persisting partial progress atomically as it goes. Start a build, then POLL action: "status" every few seconds until state is "done" (or "error"); calling build again while one is running just returns current progress. action: "status" reports the build state (idle|building|done|error), fetch/embed progress, index size and the active embedder. action: "stop" cancels a running build (partial data is kept and stays searchable). A partially built index is always usable for keyword search. Local embeddings are CPU-bound (see ZOTEUS_EMBEDDINGS), so large builds take a while — poll status rather than retrying build.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax items to index (default 5000, which is also the hard cap).
actionYes
library_idNo
library_typeNo
Behavior5/5

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

Discloses several behaviors beyond the annotations: background job execution, immediate return, 100-at-a-time pagination with a 5000-item cap, atomic persistence, partial index usability, and CPU-bound embedding. The readOnlyHint=false is consistent with the mutation intent, and openWorldHint=true aligns with the external embedding provider dependence.

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 a single dense paragraph, but each sentence carries necessary operational detail. It could be more scannable with bullet points per action, but it remains efficient and front-loaded with the core purpose.

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?

Despite lacking an output schema, the description explains the return semantics of status (reports state, progress, index size, active embedder), the lifecycle of actions, and side effects like stop keeping partial data. It gives enough context to invoke the tool correctly and interpret results.

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?

The description adds meaning for the action enum (explains build/refresh, status, stop) and the limit parameter (default 5000 cap). However, library_id and library_type are not described, and with only 25% schema coverage, the description does not fully compensate for those two parameters.

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 opens with 'Manage the local hybrid-search index used by zotero_semantic_search', which clearly identifies the tool's resource and action. Listing the actions (build, refresh, status, stop) further distinguishes it from sibling search-related tools.

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 instructs the user to poll status after starting a build, warns that builds are non-blocking and may take a while, and advises polling rather than retrying build. It also clarifies that calling build again during a running build just returns progress.

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/oscardvs/zoteus'

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