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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: the tool 'opens nothing by itself' and returns a step-by-step guide instead of performing the action. That distinction prevents an agent from assuming the call has side effects or produces data.

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 behavior and the hand-off to cotlet_browser_* appear early, which is good. But the closing sentence about Rosy's published API is tangential and confusing — it advertises API read coverage that is irrelevant to a tool that returns UI instructions, and the boilerplate 'from ChatGPT, Claude or any AI agent' adds nothing. Trimming those would make it tighter.

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 no parameters, no output schema and annotations covering safety, the remaining burden is explaining what the call produces and what to do next — both are stated. It does not describe the granularity or structure of the returned steps (e.g., whether it is a numbered list keyed to screens), which would fully close the gap.

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 the description neither needs nor provides parameter detail. Nothing in the description conflicts with the empty schema.

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 verb and resource ('View appointment schedule in the user's own Rosy Salon Software account') and then clarifies the non-obvious nature of the tool: it returns step-by-step UI instructions rather than the schedule itself. Sibling tools differ by resource (arrival/check-in status, client details), which the name already separates. It falls short of 5 only because the opening sentence frames it as viewing data, while the actual output is a procedure.

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 workflow: call this first to get the screens/buttons/fields, then execute with the cotlet_browser_* tools in the user's Rosy Cloud Browser. That names the follow-up alternative explicitly. What is missing is any exclusion — it never says when to prefer cotlet_app_guide or when this tool is unnecessary.

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