bnm_policy_rate_oprOvernight Policy Rate (OPR) — Bank Negara Malaysia's benchmark monetary policy interest rate. Latest OPR decision by default, or every decision in a given year (with change_in_opr and new_opr_level).
| Name | Required | Description | Default |
|---|---|---|---|
| year | No | Four-digit year, e.g. 2025. Omit for the latest OPR level. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond annotations by stating the default behavior (latest decision) and the additional fields returned when a year is specified ('change_in_opr', 'new_opr_level'). No contradictions with 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?
The description is two concise sentences, front-loading the core purpose and then explaining the parameter's effect. No redundant information.
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 simple tool with one optional parameter and no output schema, the description fully covers the needed context: default behavior, optional year, and what data is returned. It is complete for an agent to invoke correctly.
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 description adds significant meaning to the year parameter: omitting it returns the latest OPR level, while including it returns every decision for that year with change and new level. This goes beyond the schema's description, which only defines the parameter as 'Four-digit year'.
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 identifies the tool as retrieving Overnight Policy Rate (OPR) decisions from Bank Negara Malaysia, specifying the resource (OPR) and action (retrieve). It distinguishes from sibling tools like 'bnm_base_rate' by explicitly naming OPR and referencing benchmark monetary policy.
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 provides clear context: default returns the latest OPR decision, while providing a year returns all decisions for that year with change and new level. It does not explicitly state when not to use it, but the context is sufficient for a simple retrieval tool.
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 occupy clearly different niches, but ask_pipeworx and ask_pipeworx_beta are currently identical, ask_pipeworx_grounded and deep_research heavily overlap the same router concept, and bet_research/polymarket_edges/polymarket_arbitrage all target similar 'find an edge' territory. An agent would need to read very long descriptions carefully to avoid selecting the wrong tool.
Names are consistently lowercase snake_case and usefully grouped by prefixes like bnm_, polymarket_, and pipeworx_, which makes the set fairly scannable. However, conventions mix verb-first names (ask_, discover_, resolve_, validate_) with noun-phrase names (entity_profile, recent_alerts, recent_changes), so it is not a uniform verb_noun pattern.
36 tools is well beyond the typical well-scoped 3-15 tool range, and the server bundles several distinct domains: BNM data, the Pipeworx research platform, prediction-market analysis, and memory/subscription management. This breadth would be better split into separate focused servers.
The BNM-specific surface is well covered, with dedicated tools for the main series plus a generic bnm_endpoint passthrough for anything else. The broader data side is also unusually complete, with routing, grounded answers, deep research, entity resolution, profiles, comparisons, and claim verification; only minor gaps remain, such as no dedicated historical endpoint for some BNM series.