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

Annotations already cover read-only/idempotent/open-world, yet the description still adds real behavioral value: a 1-credit cost, ranked purchase-link output with only observed availability, the disclaimer that unknown facts stay unknown, and that misses are logged as agent observations rather than verified demand. It could go further on what 'ranked' means or pagination, but this is well beyond annotation restatement.

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?

Two sentences, front-loaded with the action and filter scope, and the cost/return/caveat information is packed without filler. The final clause about saved observations is terse to the point of slight opacity but still 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?

For an 8-parameter open-world search with an output schema (so return shape needn't be spelled out) and annotations covering safety, the description supplies cost, reliability caveats and filter intent. Missing only explicit sibling routing, which keeps it short of complete.

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 75% schema description coverage the schema already documents query, size, color, currency, max_price and in_stock. The description only echoes the filter families ('budget, currency, size, color and stock') without adding format or interaction detail (e.g. that max_price requires a matching currency), so it lands at the baseline.

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+resource ('Search recorded retail listings across stores') plus the filter axes it accepts, which is enough for an agent to recognize a product-listing search. The closing clause about observations vs verified human demand implicitly carves out space from siblings like check_demand, but no sibling is named explicitly.

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?

Usage is implied by 'using explicit budget, currency, size, color and stock filters' – it tells you this is the constrained-search path – but it never states when to prefer check_demand, get_gap or report_not_found instead, nor any prerequisite or exclusion. Adequate implication, no explicit routing.

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