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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, and the description is consistent with them by stating it 'opens nothing by itself'. It adds real context beyond the annotations: the return content shape (ordered steps with screens/buttons/fields), the dependency on the Evite Cloud Browser, and the absence of an official API. It stops short of stating prerequisites such as whether a browser session must be open first or which Evite UI version the steps assume.

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 action and immediately followed by the key clarification that it only returns instructions. The 'from ChatGPT, Claude or any AI agent' phrase is marketing filler that adds no selection value, and the API note, while useful, is placed last where it is least load-bearing.

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, read-only guidance tool the description covers what comes back and what to do next, which is the core need. The significant gap is that it never says how the target event or the desired change is specified to the tool, so an agent cannot tell whether it must pass context in-conversation or read it from the browser session. Prerequisite session state is also unstated.

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 a closed empty object, so there is nothing for the description to disambiguate. Baseline of 4 applies. However, the description never explains how the agent conveys which event or which change is wanted, which is the natural semantic gap for a zero-param guidance tool.

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?

States a specific verb and resource (update event in the user's Evite account) and, crucially, clarifies that it does not perform the update but returns step-by-step instructions (screens, buttons, fields). The guidance-vs-action split is unambiguous. It does not explicitly differentiate from the other evite_* siblings (create_event, add_guests), though the action verbs already separate them.

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?

Explicitly names the follow-up path: use the cotlet_browser_* tools in the user's Evite Cloud Browser to actually perform the change. It also rules out an API route by noting Evite has no public API or official MCP server. It lacks an explicit 'do not call this if...' exclusion, but the when-to-use context is clear.

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