search_datasetsSearch Brussels Open Data for datasets by keyword (city services, mobility, culture & urban data). Returns dataset_ids (pass to query/dataset_info), titles, themes and record counts.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max datasets (1-100, default 20). | |
| query | No | Keyword(s) to search dataset titles/descriptions. | |
| offset | No | Pagination offset (default 0). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering safety and side-effect transparency. The description adds keyword search behavior and pagination details but does not significantly extend beyond the annotations and schema.
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 two sentences: the first states the core purpose, and the second describes the output and downstream use. It is front-loaded with essential information and contains no fluff.
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?
Given the tool's simplicity (3 parameters, no output schema), the description covers the input (keyword search with pagination) and output (dataset_ids, titles, themes, record counts). No information is missing for an agent to use the tool effectively.
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 100% with clear parameter descriptions (limit, query, offset). The description adds value by explaining the output semantics (dataset_ids to pass, titles, themes, record counts), which helps the agent understand what the tool returns beyond the schema.
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 states the action ('Search Brussels Open Data') and the resource ('datasets by keyword'), specifying the domains (city services, mobility, culture & urban data) and the return fields (dataset_ids, titles, themes, record counts). It effectively differentiates from sibling tools like dataset_info by mentioning that ids can be passed to query/dataset_info.
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 implicitly suggests downstream use of dataset_ids but does not provide explicit guidance on when to use this tool vs alternatives, nor does it state exclusions or prerequisites. The context implies searching by keyword, but lacks direct 'use this when' language.
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 have distinct purposes, with clear descriptions differentiating similar ones like ask_pipeworx and ask_pipeworx_grounded. However, some overlap exists between deep_research and ask_pipeworx, though descriptions provide guidance.
Tool names are inconsistent, mixing snake_case (ai_visibility_check), multi-word phrases (scan_competitor_ai_presence), and simple verbs (query, recall). No uniform pattern like verb_noun convention.
33 tools is on the high side, but the server covers a broad domain (data querying, prediction markets, subscriptions). It feels slightly heavy but still manageable; borderline between reasonable and excessive.
The Pipeworx and prediction market tools are comprehensive, but Brussels Open Data is underrepresented with only three tools (query, dataset_info, search_datasets). Missing update/delete operations for Brussels data, though likely read-only.