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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful output-shape context that annotations cannot: each step carries an authority, form, link and legal norm, and texts follow the version's language. With no output schema, it could have gone further on result structure, but it does disclose the substantive content and the localization behavior.

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 purpose is front-loaded, which is good, but the middle is a long comma-chained enumeration of topics that is dense to parse. The parenthetical 'the same blocks as under the result on doubletaxation.app and in check_residency "done"' points at an external UI the agent cannot inspect, and 'Texts are in the language of the version' is terse to the point of being cryptic.

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 six-parameter tool with a nested move object and no output schema, the description covers the substantive scope of what comes back and when it applies, and the schema covers parameter meaning fully. Gaps are minor: nothing on result size or format beyond the per-step fields, and no explicit statement of how the move/year combination changes the returned steps.

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 100%, including nested move.kind/date and an explicit note that other is required for BOTH/MAP/NONE/UNDETERMINED, so the schema does the heavy lifting and a 3 baseline applies. The description only touches parameters indirectly — 'once the tax residence is known' for residence, and 'the language of the version' for version — adding no new semantics for year, move, other or citizenship.

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 opens with a specific purpose — 'What to do once the tax residence is known' — and enumerates the covered blocks (certificate of residence, resident/non-resident obligations, treaty relief, U.S. citizen rules, exit tax, year-of-move treatment). It ties itself to the sibling check_residency by referencing its 'done' state, which helps separate the conclusion from the follow-up guidance. It stops short of a crisp verb+resource statement like 'returns post-conclusion action steps', but the scope is unmistakable.

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?

'Once the tax residence is known' clearly signals the prerequisite and sequencing relative to check_residency. It also declares a boundary by promising 'what the conclusion does not cover'. There is no explicit when-not or named alternative (e.g. exit_tax_check, regime_search) despite exit tax being listed as covered here, so routing between overlapping siblings is left partly to inference.

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