montreal_datasetsSearch the City of Montreal open-data catalogue (donnees.montreal.ca, CKAN) by keyword. Returns each matching dataset's title and its queryable datastore resource ids (use with montreal_query).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max datasets (1-50, default 15). | |
| query | No | Keyword(s), e.g. "parking", "trees", "budget". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, idempotentHint, openWorldHint, and destructiveHint. The description adds value by specifying the return format (title and resource ids) and the source (CKAN). It does not mention rate limits or pagination, but the safety profile is covered by 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 well-structured sentences. First sentence states the core action and source, second sentence describes the return value and usage hint. No filler or redundancy.
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 low parameter count, complete schema coverage, and no output schema, the description provides sufficient context. It covers purpose, output, and relationship to sibling tool.
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 descriptions for both parameters (limit and query). The description does not add additional semantic meaning beyond what the schema provides, so baseline 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 verb 'Search', the resource 'City of Montreal open-data catalogue', and the output 'title and its queryable datastore resource ids'. It distinguishes from sibling tools like montreal_query by mentioning that the ids can be used with 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 implies when to use the tool (to search datasets by keyword) and how to chain it with montreal_query. However, it does not explicitly state when not to use it or compare directly with siblings like montreal_recent.
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 detailed descriptions, but ask_pipeworx_beta is explicitly identical to ask_pipeworx, and the several polymarket tools (bet_research, polymarket_edges, polymarket_arbitrage) have overlapping prediction-market territory. Descriptions help differentiate, but the overlaps could still cause misselection.
The majority follow a clear verb_noun snake_case pattern (e.g., compare_entities, resolve_entity, generate_llms_txt). A few tools deviate with noun/adjective prefixes (montreal_datasets, montreal_recent, pipeworx_feedback, recent_alerts) or single verbs (remember, recall, forget), but the overall style is consistent and readable.
At 34 tools, the set exceeds the 25+ threshold and feels heavy. While each tool has a distinct role, the sheer number—spanning data access, prediction markets, memory, subscriptions, and meta-tools—makes the surface harder for agents to navigate compared to a more focused server.
For its broad data-gateway purpose, the server covers a wide range: lookups, research, entity resolution, claim validation, memory, subscriptions, and feedback. The Montreal-specific subset (datasets, query, recent) is adequate for the apparent scope, with only minor gaps like no subscription-update tool.