oldnavy_search

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

With no annotations to lean on, the description discloses a crucial behavioral trait: this is a best-effort search that falls back to recommended results for obscure or nonsense keywords, with no reliable signal to tell a true keyword match from fallback. It also states the return shape (pricing, review scores, purchasable color variants). It does not mention pagination quirks or read-only side effects, but search tools are reasonably assumed non-mutating.

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 core purpose and brand mapping are front-loaded into the first two sentences. The second half about fallback behavior is a dense caveat, but every sentence carries necessary operational information. There is no filler, though the prose is slightly long.

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 three-parameter tool with no output schema, the description covers the essential return content and the critical fallback caveat. The omission of page-size or response-field details is a minor gap given the context signals, but the description tells an agent enough to invoke the tool correctly and interpret its output.

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?

The schema already has 100% parameter descriptions, so the baseline is 3. The description adds the exact enum-like values for brand (`on`, `gap`, `br`, `at`), the default (`on`), and clarifies keyword interpretation by exposing the fallback behavior for obscure or nonsense terms. This goes well beyond the schema descriptors.

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 action ('Search') and a definite resource ('Old Navy, Gap, Banana Republic, or Athleta products'), and further defines the resource as 'product listings' with a 'normalized product summaries' return. It distinguishes from product-detail/category sibling tools only implicitly, so it stops short of the strongest sibling-differentiating statement.

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?

It tells the agent how to select the storefront via the `brand` parameter, including exact values and the default (`on`). It also warns about fallback behavior for obscure keywords. However, it never explicitly says when NOT to use this tool or points to alternatives such as oldnavy_product, oldnavy_category, or oldnavy_categories.

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