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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description is consistent with them: "opens nothing by itself" confirms the non-mutating nature. It adds genuinely useful context beyond the annotations by specifying the return content (step-by-step screens, buttons, fields) and noting there is no official MCP server, which explains why a browser handoff is required.

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 critical behavioral fact (it only returns instructions) is front-loaded, which is good, but the sentence bundles the return value, the browser handoff, and an API audit note into one run-on clause. The "from ChatGPT, Claude or any AI agent" framing and the dated "checked 17 Oct 2026" remark consume space without helping an agent decide or invoke.

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 zero parameters, no output schema, and annotations covering the safety profile, the description carries the right amount of load: it states what is returned and which tool family continues the workflow. It does not specify what platform/version screens the guide assumes, a minor omission for a guidance-only tool.

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 fully specified, so there is no parameter meaning to add. Baseline of 4 applies; nothing in the description misrepresents the empty input.

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 names a specific verb and resource ("Schedule post in the user's own Ghost account") and explicitly corrects the natural misreading by stating it "Returns how to do it in Ghost step by step (screens, buttons, fields) and opens nothing by itself." That distinguishes it from ghost_create_draft_post, though the name/behavior gap (it guides rather than schedules) keeps the framing slightly indirect.

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 path: call this to get the procedure, "then do it with the cotlet_browser_* tools in the user's Ghost Cloud Browser," which names the concrete alternative family for execution. It lacks an explicit exclusion (e.g., when to prefer ghost_create_draft_post or Ghost's REST Admin API instead), so it stops just 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.