add_items

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses batch behavior (single API call), validation behavior (invalid fields/creatorTypes rejected with helpful errors), default creatorType behavior, and the ability to add custom fields. It does not explicitly mention auth requirements, reversibility, or response format, but it covers the most important behavioral traits for correct invocation.

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 long but tightly structured with bold section headers, bullet lists, and a quick reference table. Every section serves a distinct purpose: purpose, when to use, batch behavior, common fields, type-specific fields, creators, and error handling. It is front-loaded with the main action and differentiators, and the length is justified by the complexity of covering 37 item types.

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 high-complexity tool with no output schema, the description is remarkably complete. It covers usage alternatives, parameter semantics, batch behavior, field validations, creator rules, and error reporting. The only minor omission is the exact success response shape, but given the scope of the description and the presence of schema details, the agent has enough context to correctly select and invoke the tool.

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?

Although schema coverage is 100%, the description goes far beyond the schema. It explains that 'items' is an array for batch operations, provides a quick reference of type-specific fields (journalArticle, book, thesis, etc.), and details the creators structure including institutional creators and primary creatorTypes per type. It also tells the user how to obtain collection_key from create_collection or get_collections. This significantly enriches parameter understanding.

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: 'Add items to Zotero by providing metadata directly.' It clearly distinguishes this from the sibling add_items_by_doi tool by explicitly stating when to use each, including a note that add_items supports all 37 Zotero item types. The purpose is unmistakable and well-differentiated.

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 'WHEN TO USE' section provides explicit guidance: use it for items without DOIs, when full metadata control is needed, and it even specifies a mixed-batch strategy calling add_items_by_doi for DOIs and add_items for the rest. It also names the preferred alternative (add_items_by_doi) when DOIs are available and no overrides are needed. This is exemplary usage guidance.

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