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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the description reinforces this with 'opens nothing by itself,' which is genuinely useful disambiguation. It also adds the non-obvious context that AnyList has no public API, explaining why browser automation is the path. It stops short of saying whether the Cloud Browser must be opened first or whether the account is pre-authenticated.

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 purpose is front-loaded, but the first sentence pads with 'from ChatGPT, Claude or any AI agent,' which adds no selection value, and the trailing '(checked 25 Oct 2026)' API note is dated noise. The core routing sentence about cotlet_browser_* tools is the only high-value content and sits in the middle.

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?

With zero parameters, no output schema, and strong annotation coverage, the description supplies what is missing: that the return is procedural instructions and that execution happens through browser tools. It would be fully complete if it stated the prerequisite state (browser open, user signed in) before the follow-up calls.

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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. The schema is fully closed (additionalProperties: false) and the description correctly implies no input is needed. No semantic gap exists to penalize.

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 names a specific resource (shopping lists in the user's own AnyList account) and clarifies the real output: step-by-step instructions (screens, buttons, fields) rather than data. It distinguishes itself from siblings by pointing at cotlet_browser_* tools. The only weakness is the residual tension between the name/title ('List shopping lists') and the actual behavior ('returns how to do it ... opens nothing by itself'), which an agent must read carefully to reconcile.

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 sequences usage: call this to get the steps, 'then do it with the cotlet_browser_* tools in the user's AnyList Cloud Browser.' That is clear context for when to use it and what to do next. It does not name an exclusion or say when NOT to use it versus siblings like cotlet_app_guide, so it falls short of a 5.

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