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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the bar is lower; the description still earns credit by explicitly resolving the name/safety tension ('opens nothing by itself') and describing the shape of the return (step-by-step screens, buttons, fields). It adds no information about pacing, length, or failure modes of the guide, and the closing note about AccuRanker's official API/MCP server adds no operational behavior.

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 operative instructions are reasonably front-loaded, but the first sentence is overstuffed ('from ChatGPT, Claude or any AI agent') and the final sentence about an official API/MCP server with a 'checked 23 Oct 2026' stamp is tangential marketing/verification boilerplate that does not help an agent invoke the 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?

There is no output schema, so the description must carry the return-value burden; it does so only at a high level ('step by step (screens, buttons, fields)'). For a zero-parameter guide tool this is close to adequate, but it omits what the guide covers for adding keywords specifically (domains, search engines, groups) and any preconditions for the follow-up browser steps.

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 nothing for the description to disambiguate; baseline 4 applies. It correctly implies no input is required from the agent.

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 eventually makes clear that the tool returns a step-by-step guide ('screens, buttons, fields') rather than performing the add, which is a specific and useful distinction given the name. But the opening sentence 'Add keywords in the user's own AccuRanker account' frames it as the write action itself, so an agent must read to the second clause to learn what the tool actually does. It also never distinguishes itself from sibling write tools such as accuranker_add_tags_to_keywords or accuranker_add_domain.

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 workflow handoff ('then do it with the cotlet_browser_* tools') and a negative constraint ('opens nothing by itself'), which is real routing guidance. It does not say when to prefer this guide over the sibling add_* tools, nor any prerequisite about the user's AccuRanker Cloud Browser being open.

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