beste_in_categorieOnze ranglijst van de beste producten in een categorie (bijv. eiwitten, creatine, pre-workout).
| Name | Required | Description | Default |
|---|---|---|---|
| markt | No | Markt/land voor prijzen, links en codes (standaard nl). | nl |
| categorie | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the operation as read-only and non-destructive. The description adds that the result is a ranking but does not disclose ranking criteria, number of results, or whether output includes prices/links/codes (the schema's markt description hints at these). No contradiction with annotations.
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?
One short sentence conveys the purpose and examples without filler. The key phrase 'ranking of the best products' is front-loaded.
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 read-only two-parameter tool, the description is mostly adequate, but with no output schema it should specify more about what the ranking contains (e.g., products, scores, prices/links/codes) and how many results are returned. The markt description in the schema covers market-specific output, but ranking behavior itself is under-specified.
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 categorie parameter has no schema description, but the text adds domain examples (eiwitten, creatine, pre-workout). The markt parameter is well documented in the schema. With 50% schema coverage, the description partially compensates but gives no exact accepted category values or formatting guidance.
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 names the resource ('ranking of best products in a category') and supplies concrete category examples, so an agent can understand what the tool returns. It stops short of an explicit verb and does not directly contrast with sibling tools like zoek_producten, but the ranking scope is reasonably distinctive.
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 examples imply the tool is for retrieving a category's top products, which is a usable hint. However, there is no explicit when-to-use/when-not-to-use guidance or mention of alternatives such as zoek_producten or product_oordeel.
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.
Most tools target distinct concerns: current sales, expected sales, weekly deals, price history, product reviews, discount codes, and search are clearly separable. The main risk is that actuele_sales, verwachte_sales, and week_deals all deal with 'sales/deals', but their temporal and channel scopes are explicit enough to prevent serious misselection.
All tool names use lowercase snake_case and are Dutch descriptive phrases, which gives a coherent feel. The pattern is not strictly verb_noun because most names are noun phrases like product_oordeel and prijs_historie, with zoek_producten as the only verb-led exception, so the set is consistent but not perfectly uniform.
Nine tools is well within the ideal range for a supplement deals/reviews domain. Each tool covers a distinct information need without obvious redundancy or bloat.
The set covers the full user journey for supplement research: searching products, checking current deals, anticipating future sales, validating discounts with price history, retrieving discount codes, reading quality scores, and understanding the scoring methodology. No significant operational gap is apparent for the stated domain.