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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the safety profile is partly covered. The description adds real behavioral context beyond that: changing the fiscal year recalculates the year of existing vouchers, and the operation is refused when locked periods exist. It still omits required permissions/authorization context.

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?

Two sentences, front-loading the purpose before the argument enumeration, with zero filler. The long parameter clause is justified by the 0% schema coverage, though it is quite dense and would benefit from tighter grouping.

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?

For a 10-parameter mutation tool with no output schema and no schema-level descriptions, this covers every parameter plus the key side effect and failure condition. It stops short of describing auth requirements or what is returned, but nothing critical for a correct call is missing.

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 description coverage is 0% across 10 parameters, so the description must carry the burden — and it does. It labels company_id as the required argument, marks the rest optional, gives the fiscal_year_end_month range (1-12), the accounting_method enum (faktura|kontant), the ISO date format and 18-month cap for first_fy_start/end, and the semantics of clear_first_fy=true.

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?

States a specific verb and resource ("Ändra ett bolags inställningar") and enumerates the exact settings affected (name, city, fiscal year, VAT period, accounting method). An agent can immediately distinguish this from get_company, create_company, or search_company.

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?

Usage is implied: it modifies an existing company's settings, and it names a hard precondition (mutation is denied if the company has locked periods) plus a 'Scope book' requirement. However, it never routes to alternatives such as create_company for new entities or get_company for reads, so the when-to-use guidance stays implied rather than explicit.

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