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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context the annotations cannot convey: only USABLE codes are returned, codes repeat across rate changes so the caller must match on booking date, and an empty result is expected for non-VAT companies. The rate-as-fraction and entered_net semantics are arguably field documentation rather than behavior, which keeps it from 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?

Dense and front-loaded: the resource comes first, then field semantics, then the usage instruction and the edge case. The long parenthetical field glosses make it slightly run-on, but every clause carries information an agent needs to interpret the response correctly.

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?

There is no output schema, and the description compensates by documenting every returned field, including the non-obvious ones (rate as a fraction, entered_net, kind, duplicate codes across rate changes). For a one-parameter read tool this is sufficient for an agent to call it and interpret the result without follow-up.

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?

There is a single parameter, company_id, and schema description coverage is 100% – the schema already explains it is a list_my_companies value. The description adds no further meaning to the parameter itself, so the baseline of 3 applies.

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 verb-resource pairing ('The company's USABLE VAT codes') and then enumerates exactly what each returned record contains (id, code, name, rate, kind, entered_net, vat_only, validity dates). It implicitly separates itself from list_vat_periods and get_vat_statement by being about the codes themselves rather than periods or statements, though it never names a sibling explicitly.

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?

'Read it before putting a VAT code on a booking' gives a concrete trigger, and the closing note that a non-VAT-registered company has no codes to use is a useful exclusion that prevents a pointless call. There is no explicit statement of when to prefer a different tool, so it stops 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.