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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds the crucial non-obvious behavior: the tool 'opens nothing by itself' and only returns instructions, which must then be executed through browser tools. That is the single most important thing an agent needs to know for a tool whose name sounds like a mutation. It stops short of describing output structure or failure modes in any detail.

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 workflow is front-loaded in the first sentence, which is good. However, the final sentence about Salonist's Expert-tier API access and widget-only public API is tangential to the call decision and is anchored to a dated check ('8 Nov 2026'), adding length without changing how an agent invokes the tool. Semicolon-chained clauses make it denser than necessary.

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 and no output schema, the description must carry the return-value burden, and it does: it specifies that the response is a step-by-step walkthrough of screens, buttons, and fields. Combined with the explicit statement that nothing is opened or changed, an agent has everything needed to call it and act on the result.

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. One minor gap: with no inputs, it is worth stating explicitly that the returned guidance is generic rather than scoped to a specific appointment, which the description leaves unstated.

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 (reschedule an appointment in Salonist) and immediately clarifies the actual output: a step-by-step guide of screens, buttons, and fields rather than a performed action. The leading phrase 'Reschedule appointment' could momentarily read as an execution tool, though the same sentence resolves it. It implicitly separates itself from the cotlet_browser_* siblings that do 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?

It states the use context (the user's own Salonist account, via ChatGPT/Claude/AI agent) and the follow-on action: do it with the cotlet_browser_* tools in the Salonist Cloud Browser. It does not name alternatives or exclusions, e.g., whether salonist_book_appointment should be used for a new booking instead of a reschedule, so the routing guidance is clear but not exhaustive.

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