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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with them by stating it 'opens nothing by itself'. The description adds useful behavior context — returns screen/button/field steps rather than performing the send, and requires the Cloud Browser. It does not state prerequisites (campaign must already exist, browser session state) or the shape/length of the returned guidance.

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 purpose and the 'opens nothing by itself' disclaimer are front-loaded, which is good. But the client list ('from ChatGPT, Claude or any AI agent') is marketing filler, and the final API sentence is a long run-on enumerating v2 endpoints that adds only marginal routing value.

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 essentials are covered: what it returns, that it performs no side effect, and which tool family does the actual work. The main gap is the unstated prerequisite that a campaign record must already exist before this walkthrough is useful.

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 takes zero parameters, so there is nothing for the description to disambiguate. Per the baseline for parameterless tools, a 4 applies; the description's implicit point that everything is identified in-conversation rather than via arguments is consistent with that.

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 opening verb+resource ('Send campaign in ... EmailOctopus') is immediately corrected by the decisive clause 'Returns how to do it in EmailOctopus step by step ... and opens nothing by itself', so an agent learns this is a guidance tool, not an executor. It also points at the cotlet_browser_* family as the actual execution path. It does not differentiate from the sibling emailoctopus_schedule_campaign, which is a near-identical adjacent action.

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?

Usage is stated clearly: call this to get the UI walkthrough, then perform the action with cotlet_browser_* tools in the user's EmailOctopus Cloud Browser. The API-gap note justifies why a browser route is required at all. It gives no explicit 'when not to use' or guidance vs. schedule_campaign or duplicate_campaign.

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