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 safety and repeatability are covered without help from the description. The description adds real value by disclosing what the response conceptually contains (determined rate, reverse-charge determination, EN 16931 category code, legal text), which matters given there is no output schema. It is silent on authentication, failure modes for invalid VAT numbers, and whether an incomplete VAT ID silently downgrades to a chargeable rate.

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?

One dense, front-loaded sentence lists the capabilities in priority order, followed by a short endpoint parenthetical. No filler sentences; the only cost is that the endpoint detail is arguably noise for an agent that never constructs HTTP calls directly.

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 6-parameter, no-output-schema calculation tool, the description should carry the return-value burden, and it does only at a headline level (it names the outputs without their shape). Combined with zero parameter explanation and no guidance on the two required versus four optional inputs, it is adequate to identify the tool but thin for calling it correctly on edge cases like a missing or invalid buyer VAT number.

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%, so the baseline is 3, but the schema's own descriptions are pure restatements ("Parameter 'amount_type' (e.g. \"net\")") with no enumerated values. The tool description adds nothing about the parameters: it never states that amount_type drives whether VAT is added or extracted, that supply_type selects the EN 16931 category, or what buyer_vat_number is required for even though it is optional.

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?

"EU Cross-Border VAT Rate & Reverse-Charge Calculator" names a specific verb (calculate) and a specific resource (EU cross-border VAT), and the body enumerates the concrete outputs: rates, B2B reverse charge, EN 16931 tax category codes, mandatory invoice legal text. It is clearly distinguishable from generic siblings like tinplate_invoice_validator by domain, but it never names an alternative so an agent must infer the boundary itself.

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?

Usage is only implied by the domain vocabulary (B2B reverse charge, invoice legal text); there is no explicit "use this when…" or "do not use for…" statement and no routing versus tinplate_eu_vat_iban or tinplate_invoice_validator. The endpoint note (POST /v1/eu-vat-calculator) is technical metadata, not selection guidance.

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