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

The annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description usefully reinforces this with 'opens nothing by itself' — a genuinely helpful clarification given the misleading 'create' name. It also explains what the caller must do next (drive the browser tools themselves). The trailing paragraph about Fortnox's public API and licence/scope requirements is external trivia that does not describe this tool's 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 behavior and next step are front-loaded and clear, but the final third of the description is an unrelated aside about Fortnox's REST API, registration, scopes and licence entitlement that does not help an agent select or invoke this zero-parameter tool. A 'checked 14 Oct 2026' date stamp adds further noise. Removing that paragraph would sharpen the definition without losing invocation-relevant information.

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 parameters and no output schema, the burden is low, and the description covers what is returned (step-by-step screens/buttons/fields) and what the agent must do afterwards. It does not describe the response format (e.g., plain text vs. structured steps) or whether it is account-specific, but those are minor gaps 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, so the baseline is 4; the description goes slightly further by telling the agent what the returned content covers (screens, buttons, fields), which is the only 'input' semantics that matters here. Nothing about parameters is missing or ambiguous.

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 the resource (customer) and clarifies the actual operation: it returns step-by-step instructions rather than creating anything ('Returns how to do it in Fortnox step by step (screens, buttons, fields) and opens nothing by itself'). The opening phrase 'Create customer in the user's own Fortnox account' briefly reads like a write operation, but the very next clause corrects it, so an agent can still tell what the tool does.

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 an explicit follow-up path: use this tool to get the procedure, 'then do it with the cotlet_browser_* tools in the user's Fortnox Cloud Browser.' That is real when/how guidance. It stops short of stating when not to use it or routing to specific Fortnox siblings for adjacent tasks, so it is strong context rather than a complete decision rule.

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