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

Annotations cover the safety profile (readOnly, idempotent, closed-world), and the description adds substantial behavior beyond them: unknown costs stay null, similar products stay separate, affiliate links never change rankings, totals are product+shipping, supplier-billed duty can be established/zero/bounded/unverified, profit is a pre-tax estimate from approved fee research, and estimated duty can never support a best-profit claim. That is real invocation-relevant context, not restatement.

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 well — the first two sentences carry the when-to-use case — but the body sprawls into a dense run of duty/VAT/profit rules ('Show one estimated duty amount using the converted upper endpoint...') that reads like output-documentation prose rather than selection guidance. Several clauses could be compressed or delegated to the output schema without losing decision value.

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 12-parameter, high-complexity comparison tool with an output schema, it covers destinations, currency coupling, null handling, duty treatment and tax exclusions. The one gap is canonicalProductId — its provenance is only implied by 'Search products first' rather than stated, so an agent must infer where the ID comes from.

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 83%, so the baseline is 3, but the description earns more: it explains that yourSupplier pins that supplier first and shows the per-sale difference on every other row, that sellingPrice and targetMargin are paired inputs requiring salesChannel/shopLocation for fees, that pricingTier must be explicitly requested with 'base' as standard, and that choices/optionKey fall back to the product's usual configuration whose label is returned. That cross-parameter dependency is not in the schema.

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 specific verb and resource ('compare print-on-demand supplier costs for a product') and immediately names the concrete comparison axes: product prices, shipping, delivered totals, delivery times. It also enumerates the supplier set and the product categories, so an agent can distinguish it from get_supplier_prices or search_products without opening a schema.

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 explicit triggers (seller asks which supplier costs less, Printify vs Printful, Etsy/Shopify fulfillment choice), explicit prerequisites ('Search products first', use get_product_options for size/color), and explicit exclusions ('Do not use for ordering, store integrations, print-quality rankings or unsupported destinations'). It also sets a re-call rule: whenever the seller mentions their supplier, selling price, margin or platform, call again with those fields.

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