recordsQuery records from an Opendatasoft dataset with optional keyword search, ODSQL WHERE/SELECT/GROUP BY/ORDER BY clauses, pagination, and projection; returns matching rows as JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| limit | No | ||
| where | No | ||
| offset | No | ||
| select | No | ||
| group_by | No | ||
| instance | No | ||
| order_by | No | ||
| dataset_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| results | No | Array of record objects | |
| total_count | No | Total count of matching records |
Changes observed during successful MCP inspections.
Input schema / examplesAdded value: +[
+ {
+ "dataset_id": "world-cities",
+ "limit": 20
+ },
+ {
+ "dataset_id": "us-census-data",
+ "limit": 50,
+ "offset": 0,
+ "order_by": "population DESC",
+ "select": "name,population",
+ "where": "population > 100000"
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "description": "Records from a dataset",
+ "properties": {
+ "results": {
+ "description": "Array of record objects",
+ "items": {
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "total_count": {
+ "description": "Total count of matching records",
+ "type": "number"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints. The description adds meaningful context by specifying the return format (JSON), pagination support, and ODSQL capabilities. This goes beyond what annotations provide without contradicting them.
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?
A single, well-structured sentence that front-loads the core purpose and uses every phrase to add value. No fluff or repetition of schema details.
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?
The description covers key behavioral aspects (keywords, ODSQL, pagination, projection, return format) for a moderately complex tool with 9 parameters. An output schema exists, so return details are not needed. Minor gaps like default pagination limits are omitted, but the description is complete enough for an agent to select and invoke correctly.
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 0% schema description coverage, the description compensates by mapping most parameters: q (keyword search), where/select/group_by/order_by (ODSQL clauses), limit/offset (pagination), and projection (select). It misses dataset_id and instance, but these are self-evident or niche; overall it gives significant semantic meaning to 7 of 9 params.
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 uses a specific verb ('Query') and resource ('records from an Opendatasoft dataset'), clearly distinguishing it from siblings like 'dataset' and 'datasets' which likely handle dataset metadata. It lists concrete capabilities (ODSQL clauses, pagination, projection) beyond a generic statement.
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 clearly indicates the tool is for querying records from datasets, with explicit references to ODSQL, pagination, and projection. It does not provide explicit exclusions or name alternatives, but the context makes it obvious when to use this tool versus sibling metadata/facet tools.
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.