Skip to main content
Glama

Zotero Synthesize Annotations

zotero_synthesize_annotations

Gather highlights, comments, and child notes from a collection, tag, or full library into a per-paper digest for you to synthesize before writing a thematic review.

Instructions

Gather highlights, comments and child notes across a scope into a per-paper digest for YOU to synthesize; no LLM is called. collection_key: only papers in that collection; omit for the whole active library. tag: a tag or list of tags to filter papers by. limit: annotations and notes scanned (default 200). format: 'markdown' (default, grouped by paper with a count summary) or 'json'. Use it before writing a thematic review.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "zotero_synthesize_annotations"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNo
limitNo
formatNomarkdown
collection_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses non-obvious traits: no LLM is invoked, the limit caps 'annotations and notes scanned', and output is grouped per paper with a count summary. It does not state read-only behavior explicitly, nor whether the scan limit truncates results or how truncation is surfaced, which matters for a tool with zero annotation coverage.

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 the purpose and the no-LLM caveat before the parameter glossary, and every clause carries information. The dense run-on parameter listing is efficient but slightly telegraphic compared with a cleanly separated structure.

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 4-parameter read tool with no output schema and no annotations, the description covers purpose, scope selection, scan limits, and output shapes well enough to call it correctly. Remaining gaps are secondary: exact digest fields in json mode and truncation/error behavior when the limit is hit.

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 description coverage is 0%, so the description must compensate, and it largely does: all four parameters (collection_key, tag, limit, format) get meaning beyond their names, including the omit-for-whole-library default behavior, the scan scope of limit, and the enum values with structural differences between markdown and json. It does not specify whether multiple tags are ANDed or ORed, leaving one real semantic 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?

States a specific verb-and-resource ('Gather highlights, comments and child notes ... into a per-paper digest') plus the scope of the operation. The clause 'no LLM is called' and 'for YOU to synthesize' clarifies that this aggregates rather than summarizes, which separates it from a raw per-item annotation fetch, though it never names zotero_get_annotations or another sibling explicitly.

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?

Gives a concrete usage cue ('Use it before writing a thematic review') and per-parameter selection guidance ('collection_key: only papers in that collection; omit for the whole active library'). It lacks explicit when-not-to-use framing or a named alternative for narrower single-item needs, so it stops short of full routing guidance.

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