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

Annotations already declare mutation, idempotency and non-destructiveness, but the description adds real behavioral context: the prerequisite that the prior year result must be booked (8999/2099) and the 'only book what remains, null if nothing remains' semantics. It stops short of describing the response or failure modes, so not a 5.

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?

Front-loaded with the core action, then when to use it, then prerequisites and argument notes. Dense but every sentence carries operational weight; only minor compression is possible.

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 scoped mutation tool with no output schema and solid annotations, the description covers action, trigger conditions, prerequisites and residual-amount behavior. It omits return/error handling, but that is a minor gap here.

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 well documented in the schema but year has no schema description. The description compensates by clarifying that 'year' is the NEW year (det NYA året), which is essential to call the tool correctly and is not derivable from the schema alone.

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 (transfer/för om) and resource (prior year result) and even names the exact accounts moved between (Årets resultat 2099 → Balanserat resultat 2091). An agent can distinguish it from siblings like lock_fiscal_year or book_year_end_step without opening the schema.

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?

Explicitly says the transfer happens automatically when the prior year is locked and to use this tool only when that hasn't occurred (e.g. older years). It names the alternative mechanism and the condition that selects this tool, leaving little to inference.

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