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

This is the definition's strongest part: it explicitly states the tool 'opens nothing by itself,' which reconciles the imperative name with readOnlyHint=true and tells the agent it is safe and side-effect free. The trailing note about Zotero's public Web API v3 is not behavior this tool exhibits (it returns instructions rather than calling the API), so it adds length without adding behavioral certainty.

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 operative information (returns steps, performs no action, hand off to browser tools) is compact and mostly front-loaded. It is diluted by vendor-name dropping ('ChatGPT, Claude or any AI agent') and an unrelated API-version claim with a date stamp, neither of which helps an agent decide or invoke.

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, read-only guide tool with no output schema, the description covers what the agent gets back (step-by-step screens, buttons, fields) and what to do next, which is the essential loop. The remaining gap is the trigger condition — what qualifies as a note request and where the content comes from — which is left implicit.

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?

There are zero parameters and schema coverage is moot, so the baseline applies. That said, the absence of parameters raises an unaddressed question — how the tool knows which note is wanted — and the description does not explain that the target is derived from conversation context rather than inputs.

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 does eventually say what the tool produces — step-by-step instructions with screens, buttons and fields — which is specific. But the leading claim, 'Create note in the user's own Zotero account,' points the opposite direction from what the tool actually does, so the real purpose is buried in the second clause. An agent skimming the first sentence could easily expect a note to be created rather than a guide to be returned.

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 gives a clear follow-on path: obtain the steps here, then execute them with the cotlet_browser_* tools in the user's Zotero Cloud Browser, so the agent knows where this tool sits in a sequence. What is missing is any exclusions or comparison against the sibling zotero_* tools (add_item_by_doi, search_library, etc.), leaving the agent to infer when this guide is not the right choice.

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