target_search

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

With no annotations provided, the description carries the full burden, and it delivers meaningful behavioral context: what is returned (normalized products + all filter groups/options), the round-trip filter_ids interaction, the no-results semantics, and the accepted sort enum values. It does not mention authentication, rate limits, or potential side effects, but for a search tool these are less critical and the provided details go beyond the schema.

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 description is four sentences, all dense with useful information and no filler. It front-loads the core purpose, then progressively details the filter mechanism, no-results behavior, and sort options. Every sentence earns its place.

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 there is no output schema, the description reasonably communicates the high-level response shape (products, total, filter groups/options) and the key invocation details (filter_ids, sort values). It does not exhaustively describe product fields or filter group structure, but for a search tool with five parameters this is a practical level of completeness.

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 value by enumerating the valid sort values ('relevance', 'featured', 'price-low', 'price-high', 'rating', 'bestselling', 'newest') that the schema only vaguely describes as 'Result order'. It also clarifies how filter_ids interacts with the returned filter groups, which adds semantic meaning beyond the schema's generic 'Comma-separated Target filter option ids'.

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 opens with a clear verb-resource pair ('Search Target products') and immediately specifies the key differentiator from sibling tools: it returns normalized products plus every filter group and option for the result set. This distinguishes it from target_product, target_categories, and target_filter_options by describing its combined search+filter-faceting behavior.

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 clear operational guidance: how to use filter_ids (pass option ids back as a comma-separated list), and that a zero total with an empty products list is a valid no-results response. It implies when to use this tool (for search with filter faceting) but does not explicitly name alternatives or state when not to use it, so it misses the top criterion.

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