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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so safety is covered; the description adds genuinely non-obvious behavior: rounding up to whole CZK, terminating exactly at acquisition cost, refusing years outside 2008–2027, and emitting a warning (not a computation) for § 30a extraordinary depreciation. It does not describe the shape of the returned schedule, but with no output schema that is a minor gap.

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 purpose before the legal detail, and nearly every clause earns its place (method, groups, rounding, year window, threshold, warning). The English restatement roughly doubles the length and is largely redundant for an agent, which is the only real inefficiency.

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 self-contained calculator with no output schema, the description covers computation rules, valid input ranges, rounding, and edge-case behavior (out-of-range years rejected, § 30a only warned about). What is missing is any hint at the result structure — e.g. a per-year table — which the agent must infer.

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 100%, so the baseline is 3, but the description adds real meaning beyond it: it narrows rok_zarazeni to 2008–2027 although the schema permits 1990–2100, ties zvyseni_10 to groups 1–3 and excludes passenger cars, and states the 40,000/80,000 CZK threshold split by year. These constraints are 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?

Opens with a concrete verb+resource ('Sestaví daňový odpisový plán hmotného majetku') and pins it to § 30–32, naming both supported methods (rovnoměrně § 31, zrychleně § 32). No sibling tool covers depreciation, and the scope is stated so precisely that the agent needs no schema to identify it.

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?

Gives strong context: which assets, which years (2008–2027), which groups, and two explicit exclusions — it does not classify assets into groups ('Majetek do skupiny nezatřiďuje') and does not compute extraordinary depreciation ('které nepočítá'). It never routes to an alternative sibling or says when another tool is the better pick, so it falls short of a 5.

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