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

Annotations declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with them by explicitly stating it 'opens nothing by itself.' It adds genuinely useful behavioral context the annotations cannot convey: the return value is a screen-by-screen walkthrough with buttons and fields. The API/MCP aside is contextual rationale rather than behavior.

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 two-clause sentence is front-loaded and effective, but the final sentence about Resource Guru's REST API, OAuth 2 and the read-only official MCP server is a long tangential run-on that reads like research notes. It explains why the browser path is needed, but it is disproportionate to the tool's actual job and dilutes the actionable instruction.

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 output schema, the description carries the burden of explaining what comes back, and it does so ('step by step (screens, buttons, fields)'). An agent knows what to expect and which tools to chain next. The only gap is not stating that no arguments are accepted or what to do if the browser session is not already open.

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 and the schema is an empty closed object, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly implies that all booking details are supplied later through the browser tools rather than here.

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 clear that despite the 'create_booking' name, the tool does not create anything itself: it 'Returns how to do it in Resource Guru step by step (screens, buttons, fields) and opens nothing by itself.' That is a specific and useful correction. It does not contrast itself with the other Resource Guru siblings (create_project, add_time_off), but the resource and deliverable are unambiguous.

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 sequence: call this to get the steps, then execute them 'with the cotlet_browser_* tools in the user's Resource Guru Cloud Browser.' That is actionable routing guidance rather than mere implication. It stops short of stating when NOT to use it (e.g., for read-only lookups where list_bookings would suffice).

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