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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and the description is consistent with that while adding genuine context: the call is a guide only, performs no navigation, and hands off to cotlet_browser_* for the real mutation. It also discloses the API-absence rationale checked on a specific date. Minor gap: it does not describe how granular or long the returned steps are.

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 statement is front-loaded, but the second sentence is a run-on that crams in the ChatGPT/Claude/agent framing and the handoff, and the 'no public documented REST API (checked 11 Oct 2026)' clause reads like boilerplate appended rather than integrated. The 'from ChatGPT, Claude or any AI agent' phrase is audience filler that does not help an agent decide or invoke.

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, no-output-schema guidance tool, the description covers what it returns, that it has no side effects, and which tools to use next. It would be stronger if it sketched the immediate next step, such as opening the browser before reading the instructions, since the agent must otherwise derive the cotlet_browser_* sequence itself.

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 and 4 is the baseline. The description correctly implies a stateless, input-free call, and no parameter meaning is left unclear.

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 makes the specific resource (a booking in the user's own BookingKoala account) and the actual deliverable (step-by-step screens, buttons, fields) clear, and explicitly states it 'opens nothing by itself' — correcting what the verb 'cancel' in the name might imply. It stops short of naming the look-alike sibling cancel_booking, so the agent must infer which of the near-identical names is the guide vs. the actor.

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 two-step workflow: call this to get instructions, then perform the action with the cotlet_browser_* tools. It also justifies the browser path by noting BookingKoala has no public documented REST API. It does not explicitly say when NOT to use this (e.g., versus bookingkoala_refund_charge or cancel_booking), leaving that boundary to inference.

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