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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false, and the description is consistent with them by stating it 'opens nothing by itself.' It adds useful context beyond the annotations: the exact return shape (step-by-step screens, buttons, fields) and the rationale that Skedda has only a read-only beta API and no official MCP server, which explains why a browser handoff is required. It says nothing about authentication requirements or what to do if the step-by-step guide doesn't match the live UI.

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?

Three sentences, front-loaded with the outcome and the critical caveat that it only returns instructions. The closing note on Skedda's API status earns its place by justifying the browser handoff, though 'from ChatGPT, Claude or any AI agent' is filler and the '(checked 31 Oct 2026)' stamp adds little for an agent selecting a tool.

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 correctly explains what comes back (a step-by-step guide) and what to do next, which covers the main gap. However, a zero-parameter cancellation tool leaves the agent with no stated path for identifying which booking to cancel or confirming success afterward — the description should point to skedda_list_bookings or describe the confirmation loop.

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 no parameter meaning for the description to add. Baseline 4 applies. One could argue the description should explain how booking identity is conveyed without parameters, but that is a completeness issue 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 names the resource and outcome (cancel a booking in the user's own Skedda account) and then explicitly corrects the expectation set by the name: it 'Returns how to do it in Skedda step by step (screens, buttons, fields) and opens nothing by itself.' That resolves the ambiguity between acting and instructing, though the leading verb 'Cancel booking' still reads as an action at first glance. It does not differentiate itself from siblings like skedda_list_bookings or skedda_create_booking.

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 context (cancelling a booking in the user's own account) and an explicit handoff: do the actual cancellation 'with the cotlet_browser_* tools in the user's Skedda Cloud Browser.' What's missing is any guidance on prerequisite steps — e.g., locating the booking first via skedda_list_bookings — which matters given the tool takes no parameters.

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