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

Annotations already declare readOnly/non-destructive/idempotent, and the description earns its credit by adding what the tool actually returns (a step-by-step guide of screens, buttons, fields) and emphasizing that no browser session is opened. The note that Evite has no public API or official MCP server explains why the browser-tool hand-off exists, though it does not discuss whether the returned steps can go stale.

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 behavior is front-loaded and easy to parse, but the phrasing carries marketing padding ("from ChatGPT, Claude or any AI agent") and a dated audit parenthetical ("checked 11 Oct 2026") that consume space without helping an agent decide or invoke. The essential contract could be stated in roughly half the words.

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 parameters and no output schema, the description carries the burden of explaining the return value, and it does: a step-by-step walkthrough plus the instruction to act via cotlet_browser_*. Nothing critical is missing for correct invocation, though noting any limits on the returned guidance would round it out.

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 with additionalProperties=false, so there is nothing for the description to disambiguate. Baseline for a no-parameter tool applies; the description appropriately avoids inventing input semantics.

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 uses a specific verb and resource ("message guests in the user's own Evite account") and immediately clarifies the mode of action: it returns step-by-step instructions rather than performing the messaging. That distinguishes it from action-performing siblings, but it never names the closest Evite siblings (e.g. evite_add_guests) to make the boundary explicit.

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 use context and the follow-on flow: call this to obtain screens/buttons/fields, then execute with cotlet_browser_* tools in the user's Cloud Browser. It also states an implicit exclusion by saying it "opens nothing by itself" (don't expect the message to be sent). It stops short of naming when a different Evite tool would be the right choice.

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