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

Annotations already declare readOnlyHint, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: no side effects occur ('opens nothing by itself'), the return is an instructional walkthrough, and execution is delegated to browser tools. The API/MCP-server background note adds little actionable 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 core message (returns steps, performs nothing, use browser tools next) is front-loaded in the first two clauses. The trailing sentence about Skiddle's public API being in beta and having no official MCP server is tangential justification rather than call-relevant guidance, and the future-dated 'checked 31 Oct 2026' adds noise.

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 input parameters and no output schema, the description carries the burden of explaining the return value, which it does ('step by step (screens, buttons, fields)'). It also tells the agent what to do afterward. It could specify prerequisites (e.g., whether an authenticated Skiddle Cloud Browser session must already exist) but is otherwise sufficient.

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-level misinformation is present.

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 concrete output ('returns how to do it in Skiddle step by step (screens, buttons, fields)') and explicitly negates the action implied by the name ('opens nothing by itself'). This distinguishes it from the cotlet_browser_* tools that actually perform the steps. Slight deduction because the tool name/title says 'Create discount codes', which conflicts with the guide-only nature and requires the reader to reconcile it.

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 names the follow-on tool family explicitly: 'then do it with the cotlet_browser_* tools in the user's Skiddle Cloud Browser', which tells the agent the correct sequence and alternative. It does not state when to avoid this tool (e.g., if no Skiddle Cloud Browser session exists), so it stops short of full when/when-not coverage.

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