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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds the genuinely important behavioral fact behind those hints: 'opens nothing by itself'. It also discloses the return shape (step-by-step screens, buttons, fields) and the fact that a browser session is required to actually perform the action. Missing: what happens if the account lacks permission, or how the steps behave if the UI differs.

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 key fact (it returns instructions rather than creating) is front-loaded, which is good. But several clauses do not earn their place for an agent selecting the tool: the 'ChatGPT, Claude or any AI agent' framing, the dated API audit note ('checked 31 Oct 2026'), and the GraphQL/no-official-MCP aside.

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 schema, no output schema, and coarse annotations, the description carries the burden and mostly does: it states that nothing is executed, what is returned, and which tools complete the job. It could say more about what the returned steps assume (logged-in session, which Ordrestyring screens) but is adequate for a guide-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 description correctly presents it as a no-input guide, so there is no parameter meaning to add. Baseline for a 0-parameter tool is 4; nothing here is misleading about inputs.

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 uses a specific verb and resource and, importantly, corrects the impression created by the name: the tool does not create anything, it 'Returns how to do it in Ordrestyring step by step (screens, buttons, fields)'. That is a clear, testable purpose. It stops short of explicitly distinguishing itself from order-adjacent siblings such as ordrestyring_create_invoice_draft.

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 usable workflow: get the steps here, then execute them 'with the cotlet_browser_* tools in the user's Ordrestyring Cloud Browser', which routes the agent to the correct next tool family. There is no explicit when-not-to-use statement or prerequisite/auth guidance, so it is clear context rather than full routing guidance.

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