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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: it returns screen/button/field-level guidance and 'opens nothing by itself', which explains why the read-only hint is accurate and what the agent must do next. It stops short of describing output format or length of the returned guide.

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 constraint ('opens nothing by itself') is front-loaded and the workflow step follows immediately, so the ordering is sound. Some wording is filler ('from ChatGPT, Claude or any AI agent', 'Exact Online's official API: Yes') that does not help an agent decide or act.

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 does the necessary work of telling the agent what comes back (step-by-step instructions with screens, buttons, fields) and what the next tool call should be. Given the trivial zero-parameter surface, this covers what an agent needs to invoke it correctly; only the guide's scope or format is left unstated.

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 applies; the description correctly implies no inputs are required to get the guide. Nothing in the description conflicts with or needs to compensate for the empty schema.

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 ('Create sales invoice in ... Exact Online') and immediately clarifies that the tool actually returns step-by-step instructions rather than performing the creation, which distinguishes it from perform-style siblings. The opening verb 'Create' is slightly misleading before the clarification lands, keeping it short of a 5.

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 states a clear follow-on workflow ('then do it with the cotlet_browser_* tools in the user's Exact Online Cloud Browser'), which tells the agent when this tool is the entry point. It gives no exclusions or comparisons against siblings such as exact_online_send_invoice or exact_online_create_relation, so routing between invoice-related tools is still left to inference.

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