search_datasetsSearch SNCF Open Data for datasets by keyword (train schedules, stations, punctuality, ridership & the rail network). 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=true and idempotentHint=true, so the safety profile is covered. The description adds useful behavioral context beyond annotations, such as the specific data scope (SNCF Open Data) and the exact return fields (dataset_ids, titles, themes, record counts), which helps the agent understand what to expect. No contradictions found.
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, front-loaded with the primary action, and includes useful examples and return information without wasted words. Every sentence earns its place, making it highly efficient and scannable.
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 tool is simple (3 optional params, no output schema) and the description adequately explains the return values and how the results should be used downstream. It covers the essential context for an agent to decide when and how to invoke it, without needing further elaboration.
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 100%, with all three parameters (limit, query, offset) already described in the input schema. The description does not add significantly to parameter semantics—it only repeats the keyword concept. Per the baseline rule for high schema coverage, a score of 3 is appropriate.
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 tool's function: searching SNCF Open Data datasets by keyword. It specifies the resource (SNCF open data), the action (search), and the scope (datasets by keyword), while also listing example content types (train schedules, stations, etc.) and the return payload, which distinguishes it from generic search 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 conveys when to use the tool: when you need to find datasets on SNCF Open Data. It also provides downstream guidance by mentioning that returned dataset_ids can be passed to query/dataset_info, implicitly indicating the typical workflow. However, it does not explicitly state when not to use it or compare to alternatives like search_within.
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.
Several tools have overlapping purposes, particularly the ask_pipeworx variants (standard, beta, grounded) and the Polymarket analysis tools (bet_research, polymarket_edges, polymarket_arbitrage). While descriptions help differentiate, an agent may still select the wrong tool for a given task.
Names mix verb-initial (ask_pipeworx, compare_entities) and noun-initial (dataset_info, pipeworx_feedback, polymarket_arbitrage) patterns. The snake_case convention is consistent, but the lack of a uniform verb_noun pattern reduces predictability.
With 34 tools, the server is overloaded relative to a clear scope. Many tools are meta-tools (memory, subscription management, feedback) that inflate the count. A more focused set of 15-20 tools would be more coherent.
The tool surface covers a wide range of domains: structured data queries, entity profiles, comparisons, prediction market analysis, memory, subscriptions, and SNCF-specific data. Minor gaps exist (e.g., no dedicated weather or sports tools), but the universal ask_pipeworx compensates. Overall, users can accomplish most tasks without dead ends.