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

The annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld=false, and the description reinforces this usefully by stating the tool 'opens nothing by itself' and that the real mutation happens in the browser tools. That routing information is genuine added value. What it omits is how the DOI is supplied at all (the schema has zero parameters) and whether the returned steps are static or tailored.

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 core distinction (returns instructions, opens nothing) is front-loaded and well placed, but the parenthetical 'Zotero's official API: Zotero has a public Web API v3 with read and write access (checked 16 Oct 2026)' is justification that does not help the agent act, and a future date in that stamp is noise.

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 zero-parameter, non-destructive guidance tool with no output schema, the definition covers the essential flow, but it leaves open how a DOI is captured from the user, what happens with an invalid or ambiguous DOI, and whether the returned steps assume the Zotero Cloud Browser is already open.

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?

With zero parameters the baseline is 4, but the name promises operation 'by DOI' while nothing in the schema or description explains where the DOI comes from or how the agent should obtain it. That unaddressed input mechanism is a real semantic gap for an agent trying to call this correctly.

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 gives a specific action ('Add item by DOI') and then makes explicit that the tool itself only 'Returns how to do it in Zotero step by step... and opens nothing by itself,' so the agent can tell this is an instructional-guide tool rather than an executor. It does not clearly differentiate itself from the sibling Zotero tools (zotero_search_library, zotero_add_to_collection), naming only the generic cotlet_browser_* family that performs the actual work.

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?

There is an implied two-step workflow: read the returned steps, then perform them with the cotlet_browser_* tools in the Zotero Cloud Browser. However, the description never states when to prefer this over other Zotero siblings, nor what to do for a user not on the Cloud Browser, and gives no exclusion conditions.

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