Search the catalog of 80+ gold and silver investment coins by name, country or keyword, with optional metal filter (gold/silver). Returns a table of matching coins: slug, name, country, metal, weight in ounces. Accepts partial matches (ex: 'maple', 'france', 'libertad').
| Name | Required | Description | Default |
|---|---|---|---|
| metal | No | Filter by metal. | |
| query | Yes | Search term. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full transparency burden. It discloses the return format (a table with slug, name, country, metal, weight), the supported search fields, optional metal filtering, and the fact that partial matches are accepted. This conveys the key operational behavior expected by an agent.
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?
Three concise sentences, each earning its place: scope, output fields, and matching behavior. The main verb and purpose are front-loaded, and there is no redundant or vague prose.
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 simple two-parameter search tool, the description covers input behavior, filter options, and output fields, which is especially important given no output schema. Minor omissions like empty-result behavior or case sensitivity are not critical for 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?
The schema descriptions are minimal ('Search term', 'Filter by metal'), but the description adds meaningful semantics: query maps to name, country, or keyword with partial-match support and concrete examples; metal takes gold/silver. This goes beyond the structured schema and helps an agent craft valid inputs.
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 specific verb ('Search'), names the resource ('the catalog of 80+ gold and silver investment coins'), and identifies search dimensions (name, country, keyword). It is clearly distinct from siblings like compare_coins, get_best_price, and get_coin_specs, which address different tasks.
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 gives clear context for when to use the tool: searching by name, country, or keyword, with an optional metal filter. Partial match examples ('maple', 'france', 'libertad') further clarify expected queries. It does not explicitly name alternative tools, but the catalog search focus versus sibling pricing/spec functions implies appropriate usage.
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.
compare_prices and get_best_price are nearly identical: both accept a coin slug or name and return the same ranked list of all 11 dealer prices with in-stock status. The other tools are distinct, but this clear functional overlap creates real selection ambiguity.
All six tools follow a consistent lowercase snake_case verb_noun pattern: compare_coins, compare_prices, get_best_price, get_coin_specs, list_dealers, search_coins. Verbs are action-oriented and predictable, making the tool surface easy to navigate.
Six tools is a reasonable size for a bullion coin information and price comparison server. The count is not excessive, though one tool is largely redundant with another, so the set is slightly less tight than it could be.
The server covers the apparent domain well: searching the catalog, retrieving full coin specs, comparing dealer prices, doing side-by-side coin comparisons, and listing dealers. Minor gaps like a dedicated spot price tool or dealer detail view exist, but core informational needs are covered.
