search_datasetsSearch Rennes Métropole Open Data for datasets by keyword (mobility, urban services, environment & geography). 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). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesPrevious value: -[
- {
- "query": "mobility"
- },
- {
- "limit": 10,
- "query": "bike stations"
- }
-]New value: +[
+ {
+ "query": "transport"
+ },
+ {
+ "limit": 10,
+ "query": "vélo"
+ }
+]Input schema / examplesAdded value: +[
+ {
+ "query": "mobility"
+ },
+ {
+ "limit": 10,
+ "query": "bike stations"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, so the bar for transparency is lower. The description adds useful context: it returns dataset_ids and indicates a two-step process (pass to query/dataset_info). It also mentions the thematic scope. No contradictions. This is decent behavioral context beyond 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?
Two sentences, front-loaded with the core action, no filler. Every clause adds value: the scope, the return fields, and the linkage to other tools. Perfectly concise and structured for quick absorption.
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 three simple parameters, rich annotations, and no output schema, the description covers the essentials: what it searches, what it returns, and how the output is used. It doesn't detail pagination or rate limits, but the schema and annotations cover those. The linkage to query/dataset_info enhances completeness. A small gap: it doesn't explicitly say the search is case-insensitive or language-specific, but that's not critical.
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% for all three parameters (query, limit, offset). The description doesn't materially add to parameter semantics beyond what the schema provides, though it does mention 'keyword' which aligns with query. It adds a hint about domains but no new syntax or format details. The baseline for high coverage is 3, and the description neither improves nor worsens it.
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: 'Search Rennes Métropole Open Data for datasets by keyword' with specific categories (mobility, urban services, environment & geography). It also lists the return elements (dataset_ids, titles, themes, record counts), differentiating it from siblings like dataset_info (which likely retrieves details by ID) and query (which might execute data queries). This verb+resource+scope is precise and distinct.
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 implies when to use it: to find datasets before calling query/dataset_info, explicitly stating 'Returns dataset_ids (pass to query/dataset_info)'. This provides a workflow hint. However, it doesn't explicitly exclude other search tools or state 'use when you need to discover datasets', but the linkage is strong enough. It's clear and contextual.
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.
Many tools have overlapping purposes, such as multiple data query tools (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research) and several prediction market analysis tools (bet_research, polymarket_arbitrage, polymarket_edges, etc.). While descriptions attempt to differentiate, an agent could easily select the wrong tool.
Tool names use a mix of verb-initial (ask_pipeworx, compare_entities) and noun-phrase patterns (entity_profile, dataset_info), with no consistent verb_noun structure. Naming is readable but lacks a predictable pattern.
With 34 tools, the server is on the heavy side. The broad scope (data querying, prediction markets, company research, local open data) somewhat justifies the count, but several tools could be consolidated (e.g., the various polymarket tools).
The tool set covers a wide range of functionalities including data querying, company research, prediction market analysis, and memory management. Minor gaps exist (e.g., no user authentication tools beyond subscriptions), but the surface is largely comprehensive for its intended purpose.