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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behaviour: the number is not stored, and it introduces the 'format_check' result concept with a 'partial' strength level. However it never explains what other format_check values exist or how weak vs strong results should be interpreted, so the added value is real but incomplete.

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?

Three short sentences, each front-loaded and each carrying a distinct fact: what is checked, what it does not prove, and the side-effect guarantee. Nothing is redundant with the title, and the 'not stored' privacy line is placed last where it belongs.

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 two-parameter read-only validator with no output schema, the description covers purpose, scope and side effects adequately. The notable gap is the response shape: 'format_check partial' is referenced with no indication of what the other possible outcomes are or what other fields come back, leaving the agent guessing at the result contract.

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% (country documented, value undocumented beyond min/max length), so the description must compensate. 'Taxpayer identification number' implicitly defines the otherwise bare 'value' parameter, which is a meaningful addition, and 'the country's known format' clarifies that country selects the rule set — a non-obvious dependency the schema does not state. It does not describe accepted characters or formatting conventions for value, so it stops short of a 5.

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 ('Check whether a taxpayer identification number matches the country's known format') and immediately scopes it against the confusable neighbour concept of registration validation. An agent can tell this is a pure syntactic/format check rather than an authoritative verification.

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?

The line 'Format check only: it does not confirm registration' gives a clear use condition and an explicit non-use boundary, which is exactly the distinction an agent needs before answering a compliance question. It stops short of naming a sibling alternative for the registration case, so it is clear context rather than full routing guidance.

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