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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context by disclosing the shape of the returned data (recent_lines includes price and VAT, customers are ordered by most recently invoiced) and that customer_query searches name, org number and email. It does not discuss pagination or limits, but for a read-only setup tool this is solid.

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 content is packed into one long enumerative sentence followed by two short ones. The listing is dense but every item conveys distinct returned data, and the action-relevant instruction about customer_id and the argument summary come after the enumeration rather than being front-loaded.

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 carries the burden of describing the return value and does so thoroughly — invoice numbering, terms, accounts, recent lines, company invoice header fields, customer register and mail capability are all spelled out. Combined with the schema's orgnr documentation and the annotations, an agent has everything needed to call it and use the result.

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?

Schema coverage is 50%: orgnr is documented in the schema, but customer_query has no schema description at all. The description compensates by explaining that customer_query searches by name, org number and email, and by naming the arguments (orgnr, optional customer_query). That meaningfully closes the coverage gap.

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 enumerates exactly what this tool returns: next invoice number, payment terms, revenue account, recent_lines with price and VAT, company details, customer register and mail capability. That is far more specific than the title, though it avoids a clear leading verb such as 'hämta' and instead frames the purpose indirectly as 'Det som behövs för att skapa en kundfaktura'.

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 concrete downstream instruction — use the customer's id as customer_id in create_customer_invoice so the customer is updated — which effectively tells the agent when this tool is the right preparation step. It also mentions 'Scope view'. What is missing is any explicit when-not-to-use or reference to alternatives such as list_customer_invoices or get_company.

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