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

Given readOnlyHint=true, the description usefully explains WHY it is read-only: it 'opens nothing by itself' and only returns instructions, which preempts an agent mistaking this for a write tool. It also discloses that Ghost has no official MCP server, so browser automation is required. It stops short of describing failure modes, limits, or what happens if no Ghost account exists.

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 facts (returns instructions, opens nothing, use cotlet_browser_* next) are front-loaded in the first two clauses. The opening 'from ChatGPT, Claude or any AI agent' is promotional filler, and the parenthetical 'checked 17 Oct 2026' adds staleness risk rather than value, but the whole definition is a single tight paragraph.

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 output schema, the description correctly spends its words describing what comes back (a step-by-step visual guide). It covers the safety profile and the required follow-up tool family. It omits edge cases such as missing account, session state, or what the guide looks like when Ghost's UI differs from the expected version.

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. No parameter detail is expected or 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 a concrete resource and output: it produces step-by-step Ghost draft-post instructions (screens, buttons, fields) rather than performing the action. This resolves the mismatch between the name 'ghost_create_draft_post' and the fact it creates nothing. It is slightly less specific about payload/return shape, but the verb+resource is unambiguous.

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 workflow handoff — get the steps here, then execute them with cotlet_browser_* tools in the user's Ghost Cloud Browser — which is the main when-to-use signal. It offers no exclusion or contrast against sibling Ghost tools such as ghost_schedule_post or ghost_list_posts, and does not state prerequisites like an active browser session or a Ghost account.

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