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 saying the tool opens nothing itself. It adds genuinely useful context beyond the annotations: the return payload is procedural UI guidance rather than data mutation. It does not describe how complete or version-current that guidance is, aside from a confusing dated check.

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 and the handoff to cotlet_browser_* are front-loaded and clear. However, 'from ChatGPT, Claude or any AI agent' is filler, and the trailing sentence about ClickSend's REST API and official MCP server is tangential and ends with a stray '(checked 23 Oct 2026)' that distracts rather than informs.

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, annotation-covered guide tool this covers the essentials: what it returns and what must follow. It leaves open whether a Cloud Browser session must already be open and which cotlet_* tool establishes it, which the agent needs to sequence correctly. No output schema exists, so some indication of the guide's shape beyond 'screens, buttons, fields' would have helped.

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 closed with additionalProperties=false, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter meaning is missing.

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 states the resource (contacts in the user's ClickSend account) and immediately clarifies the real behavior: it returns step-by-step instructions and 'opens nothing by itself.' That correction is essential because the name 'add_contacts' implies a write action. It stops short of 5 only because the opening sentence restates the title and briefly reads as an action tool.

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 an explicit sequence: call this to get the ClickSend screens/buttons/fields, then execute with the cotlet_browser_* tools in the Cloud Browser. It also notes the official ClickSend MCP server is narrow, steering the agent away from that path. It does not state when to skip this tool entirely (e.g., if the browser session is already oriented), so it falls short of full when/when-not guidance.

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