Today's price cuts, new arrivals and cheapest bags per 100g across New Zealand specialty coffee. Every row carries the reason it is on the list, and an empty list carries the reason it is empty.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | all | |
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does well by disclosing two useful behaviors: every row carries the reason it is on the list, and an empty list carries the reason it is empty. It does not mention side effects, but this is clearly a read-style tool and the added output guarantees are genuinely informative.
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 only two sentences, with no filler. The core value proposition is front-loaded, and the second sentence adds a useful output guarantee that 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 a low-complexity tool with two optional parameters and no output schema, the description is reasonably complete: it covers the listing categories, geographic scope, and important output behavior. Minor gaps like ordering and explicit parameter mapping exist, but they do not prevent correct invocation.
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 description coverage is 0%, so the description needs to compensate. It partially does by naturally naming the categories that map to price_cuts, just_dropped, and cheapest_per_100g. However, it never explicitly ties those terms to the kind parameter and says nothing about limit or the 'all' option.
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 clearly identifies the tool as a source of today's price cuts, new arrivals, and cheapest-per-100g coffee listings across New Zealand specialty coffee. It does not use an explicit verb like 'list' or 'get,' but the intent is unmistakable and distinct from the sibling tools.
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 implies this tool is for surfacing deal-style listings, but it never explicitly states when to use best_deals versus roaster_info or search_beans. The sibling names provide clues, yet the description leaves the choice to inference rather than giving explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct concern: curated deals, roaster-level details, and full searchable bean catalog. Although best_deals and search_beans both surface cheap prices, their purposes are clearly separated by the deal reasons versus filterable search.
Names are readable and all snake_case, but they mix conventions: search_beans is verb-first while best_deals and roaster_info are noun phrases. A more consistent pattern would be search_beans alongside get_deals and get_roasters or similar.
Three tools is a tight, well-scoped set for a read-only specialty coffee price tracker. No tool feels redundant or unnecessary for the server's purpose.
The surface covers the full stated domain: search all beans, see curated deals, and get roaster information including shipping and stats. Agents can accomplish all advertised user goals without dead ends.