Search the Zotero library

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

Annotations already carry the read-only and non-destructive profile, so the bar is lower, and the description adds genuine behavioral context beyond them: the default match fields (titles, creators, years), what 'everything' mode unlocks (note text and indexed PDF full text), the '-' prefix semantics for tag exclusion, and the Markdown one-line-per-item output format. Nothing contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is organized into Args and Returns sections with the purpose front-loaded in a single sentence. Each parameter receives exactly one to two sentences earning its place, and the Returns section closes with the practical workflow hook (the item key). No filler, no repetition of schema defaults.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter read-only tool, the description covers search semantics, every parameter, and the return format — and an output schema exists so the return shape is further reinforced. Minor gaps remain: no mention of authorization requirements (there is a zotero_authorize_local sibling) or behavior on zero results, but nothing material blocks a correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% — the properties carry only titles and defaults — so the description carries the full burden and meets it completely. Every one of the six parameters gets semantic detail beyond the schema: item_type gets concrete examples ('journalArticle', 'thesis'), tag gets the '-' exclusion behavior, collection clarifies 'key or name', and limit gets its 1-100 range.

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

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

The description opens with a specific verb+resource statement — 'Search the library and return a compact list of matching items' — which pins down the action, scope, and output shape. This clearly separates it from siblings like zotero_advanced_search, zotero_search_annotations, and zotero_get_item, especially since the Returns section notes the item key needed by zotero_get_item and the citation tools.

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

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

Usage context is implied rather than explicit: the search_mode explanation contrasts 'metadata only (fast)' with 'everything' for full text, and the Returns section names downstream tools (zotero_get_item, citation tools). However, the description never explicitly states when to choose this over zotero_advanced_search or zotero_search_annotations, nor does it list exclusions.

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