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

The annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered upstream. The description usefully reinforces this ("opens nothing by itself") and describes the return content as screens, buttons and fields, which matters since there is no output schema. It stops short of saying whether the steps are tailored to a specific booking or generic, and gives no hint about length, caching or staleness beyond the checked date.

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 is front-loaded: what it returns, that it takes no action, and which tools to use next. Some wording is filler ("from ChatGPT, Claude or any AI agent") and the API note with a checked date reads as provenance padding, but the total length is short and every sentence carries at least some signal.

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 parameterless guidance tool the description covers the essentials: the output shape, the no-side-effect guarantee, and the handoff to browser tools. The main gap is how the agent should select the target booking given that nothing is passed in, plus no note on how detailed or long the returned steps are.

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 schema declares zero parameters at 100% coverage, so there is nothing for the description to document. Baseline for a no-parameter tool applies. One residual question the description leaves open is how the walkthrough is bound to a particular booking when nothing is passed in, but that is a scope question rather than a parameter-semantics one.

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 states a specific verb and resource ("Reschedule booking in ... BookingKoala") and immediately corrects the likely misreading of the name by saying it "Returns how to do it ... step by step" and "opens nothing by itself." That distinction is critical because the tool performs no action despite the imperative name. It falls short of 5 because it never differentiates itself from the sibling `reschedule_booking`, whose name is nearly identical, so an agent cannot be fully sure which one actually executes the change.

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?

The description names the follow-on path explicitly: get the walkthrough here, then act with the `cotlet_browser_*` tools in the BookingKoala Cloud Browser. It also gives a reason to prefer this route (no public, documented REST API). Missing is an explicit "use this instead of X" statement against the sibling `reschedule_booking`, which is the most likely source of misselection.

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