Semantic / hybrid library search

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

Even with readOnlyHint and openWorldHint annotations, the description adds crucial non-obvious behavior: the empty-index case triggers a background build, the tool instructs polling and retrying, and the hybrid behavior depends on whether an embedding provider is configured. This does not contradict the annotations and provides substantial practical context.

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 moderately long but every sentence earns its place: core behavior, mode semantics, index bootstrap behavior, and sibling-tool alternatives. It is front-loaded with the primary purpose and filters into operational details without wasted repetition.

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?

This is a nuanced tool with no output schema, and the description manages to cover the return shape ('snippet and score'), the bootstrap failure mode, the retry protocol, and relevant sibling tools. An agent has enough information to select, invoke, and recover from the only realistically surprising condition.

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 coverage is 75% and q/limit/auto_build already have descriptions, so the baseline is a 3. The description adds meaningful extra semantics for the mode enum, explaining what 'auto', 'keyword', and 'semantic' actually do, and clarifies the auto_build flow. It does not add much for q, but the schema already covers it adequately.

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 and resource: 'Search the library by meaning, not just keywords.' It clearly defines the mechanism (BM25 + vector similarity via reciprocal-rank fusion) and explicitly distinguishes this semantic tool from exact-filter search, making its purpose unmistakable.

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?

The description gives strong when-to-use guidance: use for conceptual/'papers about X' queries, and use zotero_search_items for exact field/tag/itemType filtering. It also tells the agent how to handle first-use index building: poll zotero_index action 'status' and retry, or pass auto_build:false.

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