ecb_list_dataflowsList all ECB SDMX dataflow IDs and names (e.g. EXR, ICP, BSI, MIR). Accepts an optional case-insensitive substring filter on flow_ref or name. Returns {count, total_dataflows, dataflows: [{flow_ref, name}]} — flow_ref is exactly what ecb_get_data takes as its flow_ref argument.
| Name | Required | Description | Default |
|---|---|---|---|
| filter | No | Case-insensitive substring filter |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "filter": "exchange"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior, lowering the burden on the description. The description adds useful behavioral detail beyond annotations: the filter is case-insensitive, can match flow_ref or name, and the exact return shape is disclosed. It does not contradict the 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?
Three tightly packed sentences deliver purpose, filter semantics, and return format without wasted words. The output shape is included inline, and the most important cross-tool relationship is placed at the end for emphasis.
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 has only one optional parameter, strong safety annotations, and no output schema. The description fully compensates for the missing output schema by spelling out the return object, and it connects flow_ref to ecb_get_data. Nothing needed for correct invocation is missing.
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 already describes filter as a case-insensitive substring, which is 100% schema coverage. The description adds meaning by specifying that the filter applies to flow_ref or name, and by showing how the parameter result connects to ecb_get_data. This exceeds the baseline schema-only documentation.
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 and resource: 'List all ECB SDMX dataflow IDs and names' and gives concrete examples (EXR, ICP, BSI, MIR). It clearly distinguishes this tool from data-fetching siblings like ecb_get_data by framing flow_ref as an input to that tool.
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 makes the context clear: use this when you need to enumerate available ECB dataflows and obtain the flow_ref values. It references ecb_get_data as the downstream consumer, which implicitly guides routing, but it does not explicitly state when not to use it or compare it directly with siblings.
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.
There is significant overlap between tool clusters: ask_pipeworx_beta is currently functionally identical to ask_pipeworx, and polymarket_arbitrage/polymarket_edges/bet_research all target similar opportunity-discovery tasks. While the descriptions are extremely detailed, the sheer number of similar variants makes it hard to reliably pick the right one.
Names are consistently snake_case with meaningful prefixes (ask_, ecb_, polymarket_, pipeworx_) and mostly verb-first structure. Minor deviations like entity_profile and ecb_hicp_inflation are noun-first, but they do not break the overall pattern.
35 tools is well beyond the well-scoped 3–15 range, and the surface feels bloated with redundant meta-tools (ask_pipeworx variants, deep_research, discover_tools, suggest_questions) and peripheral utilities like generate_llms_txt and scan_dependency. Many entries could be consolidated without losing function.
For the server's broad data-research domain, coverage is thoughtful and full: query, grounded answer, validation, entity resolution, profiling, comparative analysis, subscription lifecycle, memory, and feedback are all represented. Minor gaps exist (e.g., no direct raw ECB flow browser beyond generic SDMX) but nothing blocking.