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

Annotations already declare readOnly/idempotent/closed-world, and the description goes further: it says the tool resolves the subject internally, that results come from store configuration, that a limitation may be returned when nothing is configured, and that pairs must not be invented. It also bounds call cardinality (once per subject product).

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 with the use case and examples, then procedural constraints, which is the right order. The eight example phrasings are somewhat redundant and could be trimmed, but each remaining sentence carries a rule or exclusion.

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?

Given an output schema, annotations, and a nontrivial resolution/ambiguity flow, the description supplies everything needed to select and invoke correctly: trigger conditions, subject format, cardinality, failure handling, and the boundary with search and detail tools.

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 67% schema coverage the schema already explains query and product_id well; the description adds the precedence rule (known current-store ID, otherwise exact title), the fact that resolution happens internally, and the warning not to call search first to resolve. It says nothing about buyer_context, leaving one parameter covered only by 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?

States a specific verb and resource: render Complete the Look with store-configured complementary and supplementary products for a given subject product. It clearly separates itself from render_product_search (general suggestions without a subject) and product_details (which it says not to open to validate recommendations).

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 with several shopper phrasings, covers follow-up pairing requests where the subject comes from store context, and states exclusions: no automatic call after discovery search, no text-only styling substitute, ask which product when 'this/it' is ambiguous. It also names the sibling that owns the out-of-scope case (render_product_search).

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