search_items

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

Beyond the readOnlyHint annotation, the description discloses that full_text search is slower, requires a non-empty query, and raises a validation error otherwise. It also details the return shape (key/version/creators) and how to pass results to other tools, which is valuable behavioral context beyond the annotation.

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 well-structured with an opening sentence, a parameter-by-parameter breakdown, and a result-usage section. It is longer than a simple two-liner but every sentence earns its place, providing essential details without redundancy or filler.

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?

Given the tool's complexity (7 parameters, filters, pagination, full-text behavior) and the presence of an output schema, the description covers all parameters, explains return fields necessary for chaining (key/version/creators), and references related tools (list_collections, update_item, etc.). It is complete for an AI agent to select and invoke correctly.

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%, so the description fully compensates by explaining every parameter: query does substring match on title/creator/year, item_type provides examples, tag is an exact match, collection_key references list_collections, limit/start define pagination with default, and full_text has specific constraints. This goes well beyond the bare schema.

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 combination ('Search the Zotero library') and clearly distinguishes itself from siblings like get_item or list_collections by focusing on search/filter capabilities. It also states 'Read-only', reinforcing the operation type.

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 provides clear context for when to use the tool ('Search the Zotero library' or 'omit to list items') and references a sibling (list_collections) for a parameter. It does not explicitly state exclusions or alternatives like 'use get_item when you have a specific key', but the usage patterns are implied through parameter semantics.

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