create_item

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

The annotations only communicate non-read-only, non-idempotent, non-destructive behavior. The description adds meaningful context beyond that: metadata is auto-resolved, duplicates are checked, title is only used as a fallback for bare URLs, and dedup_check_failed=true is surfaced when the duplicate check fails. It stops short of explaining what happens when a duplicate is actually found, but it provides substantial transparency.

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 five sentences, each earning its place: core action, identifier types, when to use, title behavior, alternative tool, and dedup failure signal. It is front-loaded with the most important information and contains no 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?

For a tool with four parameters and an output schema, the description covers the input identifier semantics, the fallback title behavior, the alternative manual tool, and the dedup-check failure flag. The main gaps are the lack of any explanation for tags and collection_keys, and ambiguous behavior if a duplicate is found. Still, it is largely complete for an agent deciding when and how to invoke it.

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 carries the burden of explaining parameters. It gives solid semantics for input (DOI, PMID, URL) and title (fallback for unscrapable bare URLs), but tags and collection_keys are not explained at all. With four parameters and two covered, this is partial compensation rather than full.

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 a paper to Zotero from any identifier: DOI, PMID, or URL.' It clearly enumerates accepted identifier types, which distinguishes it from manual item creation and other sibling tools without needing to inspect the schema.

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?

It explicitly states when to use the tool ('Use this when the user wants to save a paper to their library') and when not to, naming the alternative: 'If you only have structured fields... use create_item_manual instead.' This is direct, unambiguous routing guidance.

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