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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds valuable behavior context: the price is computed from live metal pricing (not cached), the response includes a deep_link_url, invalid inputs return a list of valid values, and settings without a center stone are flagged in configuration/notes. No contradiction exists; the description enriches beyond annotations.

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?

Though long, every sentence serves a distinct purpose and the text is front-loaded with the core purpose. It's logically structured by product category (bands, sets, rings) and error handling, with no redundant statements. The grammar is compact and information-dense; the conciseness is appropriate for the tool's complexity.

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?

The tool is complex (16 params, nested objects, output schema) but the description covers all major aspects: identification, per-product-type configuration, defaults, error recovery, generic option mapping, and special cases (engraving, settings without center stones). The presence of an output schema reduces the need to explain return structure, but the description still mentions key return components (price, resolved configuration, deep_link_url). It is complete for the intended use cases.

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?

With schema coverage at 50%, the description compensates thoroughly. It explains the priority of variant_id vs style_code, maps named axes to specific product types, clarifies the options object as an alternative for generic jewelry, and gives examples like width='6' (mm) and stone_type='natural' or 'lab'. It also clarifies nesting for his/her objects and edge cases like engraving placement, adding significant meaning beyond 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?

The description states a specific verb and resource: 'Exact live price in USD for a fully configured item' with explicit context that it's the same number the customer pays on 25karats.com. It clearly distinguishes itself from siblings like get_product (which retrieves product data) by focusing on pricing, and from search tools by being a computation tool for configured items.

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 description provides explicit guidance on when and how to use the tool: identifies parameters for variant_id/style_code, specifies required inputs per product type (wedding bands, his & hers sets, engagement rings), explains handling of unset axes using defaults, and states that invalid values return valid ones for retry. It also warns about non-applicable inputs being rejected, giving clear when-not-to-use guidance.

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