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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds that prices are "today's best price", which signals live/freshly-computed data, but says nothing about result caps (limit max 30), what happens when filters exclude everything, or whether the speed estimate depends on the reference model default.

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 what is listed and what comes back, then the filtering/sorting controls. Dense but no filler; the parallel clauses are readable rather than padded.

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?

With no output schema, the description does the necessary work of naming the return columns (memory, bandwidth, price, model-relative speed), which is exactly what an agent needs to judge relevance. The remaining gap is behavioral/positioning detail (how the gpu_card vs machine branches differ in output, and how results are capped) rather than a missing core explanation.

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 only 44%, so the description must carry weight; it names max_price and min_memory_gb as filters and lists sort modes, which partially compensates. However, it adds no semantics beyond the schema (the sort enum already lists those values, and it even omits "popularity"), and leaves kind, condition, context and limit entirely unaddressed.

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 ("List graphics cards or complete machines") and enumerates the returned attributes (memory, bandwidth, price, estimated speed on a model). It is clear on its own, but never distinguishes itself from close siblings like best_hardware or hardware_for_model, so an agent cannot fully separate the browse case from the recommendation case from the description alone.

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?

"Filter by maximum price and minimum memory; sort by price, speed, value or price per GB" implies a browse-and-filter use case but never says when to choose this over best_hardware or hardware_for_model. The only cross-reference is inside the schema (model slug "from search_models"), not the description, so no explicit alternative routing is provided.

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