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

Annotations cover read-only and open-world behavior; the description adds far more: conditional field presence (substitutes[] only when out of stock, spec comparison only while in stock), size caps (up to 5/8/3), localization rules (guide Romanian for language=ro, English otherwise), provenance (AI-written from a sourced fact sheet), and completeness caveats (empty companions = no accessory list).

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 opening sentence is front-loaded and clear, and nearly every fact earns its place, but the body is a single dense run-on paragraph with heavy repetition ('each as a brief record with its own product_id, price and product_url' recurs three times). Breaking it into bullets and eliminating redundancy would preserve content while improving scannability.

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?

With no output schema, the description carries full responsibility for documenting return values and discharges it thoroughly: field names (substitutes[], companions[], buying_guide), shapes, sizes, conditional presence, semantics, and the agent action expected for each. An agent can call this tool and interpret its results correctly without any further lookup.

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 100%, so the baseline is 3. The description adds real value beyond the schema: it explains that prices are VAT-included and localized, and specifies how the language parameter changes output ('The guide is Romanian for language=ro and English otherwise'), which the schema's terse 'Locale for text + pricing' does not convey.

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+resource ('Get full details for one product by id') and enumerates the payload contents (description, specs, stock, VAT-included localized price). This clearly distinguishes it from siblings like search_products (discovery) and compare_products (comparison across products).

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?

Provides strong operational context: substitutes should be offered instead of searching, companions offered first when the customer wants to buy, and buying_guide used for fit questions. It never names sibling tools explicitly or states when-not conditions for tool selection, so it stops just 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.