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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds the important behavioral fact that the tool "opens nothing by itself" and merely emits procedural guidance, which prevents an agent from assuming side effects. It also flags the API-access gating (Essentials account + gateway key) as background for why browser automation is needed. It does not describe output format details or failure modes when the account is not authenticated, which keeps it below a 5.

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 disclaimer (returns steps, opens nothing) is front-loaded and useful, but the copy is padded with marketing phrasing ("from ChatGPT, Claude or any AI agent") and an awkward API tangent with a questionable date stamp ("checked 9 Nov 2026") that adds noise without helping selection. It reads as one long run-on rather than clearly separated purpose, behavior, and next-step sections.

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 guidance tool with no output schema, the description should fully characterize what comes back; it partially does by promising steps covering screens, buttons, and fields. It omits what happens if the user is not logged in, whether the guide is account-specific, and how the returned steps relate to the browser tool sequence, leaving modest gaps for a tool whose entire value is the returned instructions.

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 there is nothing for the description to disambiguate; the empty schema is self-explanatory. The description correctly implies no inputs are needed, matching the 100% schema coverage baseline.

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 verb and resource ("Find lapsed patients in ... PatientNow") and explicitly states the tool only returns step-by-step instructions rather than performing the action, which distinguishes it from the cotlet_browser_* execution tools. It does not differentiate itself from data-returning siblings such as patientnow_list_patients or patientnow_find_free_slots, so an agent must infer that this is the how-to variant.

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?

Usage is implied rather than stated: the agent learns it should call this first and then act with cotlet_browser_* tools in the PatientNow Cloud Browser. There is no explicit "when not to use", no naming of an alternative for agents that already know the PatientNow UI, and no prerequisite stated (e.g., the user must be signed into PatientNow).

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