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

Annotations only give the generic safety profile (readOnly=false, destructive=false, idempotent=false). The description adds real context beyond that: it never locks the period (a human does), it requires scope book, and it discloses that for proposal-backed steps the code — not the LLM — writes the voucher. Consistent with annotations, no contradiction.

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 verb and resource, then mode rules, then the locking/scope caveats, then the argument summary. Dense but each sentence carries distinct information; no filler.

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 non-idempotent mutation with no output schema, the description covers the posting model, scope requirement, and all arguments, which is close to sufficient. It omits error/reversal behavior and the resulting voucher reference, and the unexplained action values leave a small gap.

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 only 25% (just orgnr), so the description must compensate, and it does list step's allowed values (periodiseringar|dispositioner|aktuell_skatt|arets_resultat) plus the journal element shape ({account, debit_ore, credit_ore, text?}). However it repeatedly references action='book'/'manual', a parameter absent from the schema, which risks leading an agent to pass a nonexistent argument.

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+resource ('Bokför ett årsavslutssteg') and immediately clarifies the division of labor between code and LLM. It is distinguishable from siblings like skip_year_end_step, undo_year_end_step and create_proposal by scope, though it never names those alternatives.

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?

Clear conditional routing: action='book' when a proposal exists (the code posts the balanced voucher, LLM only picks the step), action='manual' when the user supplies their own journal. This tells an agent exactly which branch to take, but stops short of naming sibling tools (undo/skip) or stating prerequisites like checklist state.

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