exchangesReference list of exchanges Massive (formerly Polygon.io) covers: US stock exchanges (NYSE, NASDAQ, etc.), options venues, crypto exchanges, and OTC tiers. Returns MIC code, name, asset class, type, locale.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | No | ||
| asset_class | No |
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of results | |
| status | No | API response status | |
| results | No | Exchange data |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and open-world hints. The description adds valuable context about the scope (Massive/Polygon.io coverage) and output fields without contradicting annotations. It does not mention limitations like pagination, but the output schema partly compensates.
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 a single, information-dense sentence that front-loads the purpose, gives concrete examples, and lists return fields. No wasted words; every element adds value.
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 (two optional params, output schema present). The description covers purpose, coverage, and returned fields. Missing explicit parameter explanations and pagination behavior are minor gaps given the reference-list nature and output schema availability.
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 0% for parameters (locale, asset_class), and the description only vaguely hints at them by listing them among return fields. It does not explain allowed values or how to use them for filtering, leaving the agent without essential parameter guidance.
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 a reference list of exchanges, specifies covered asset classes (US stocks, options, crypto, OTC), and lists return fields (MIC code, name, asset class, type, locale). This is specific and distinguishes it from sibling tools like tickers or market_holidays.
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 usage for looking up exchange information but lacks explicit when-to-use or when-not-to-use guidance. It provides clear context but no exclusions or alternative tool comparisons, which is sufficient for a non-ambiguous reference 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.
Tools like ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded have overlapping purposes (all answer questions via a universal router), with only subtle distinctions (beta version, grounded mode). Additionally, many tools like entity_profile, compare_entities, recent_changes, and resolve_entity all pull SEC/company data, and polymarket_arbitrage, polymarket_edges, polymarket_fill_risk, bet_research all relate to prediction markets, creating potential confusion. However, each tool does have a somewhat distinct purpose and detailed descriptions help differentiate them, so it's not extreme overlap.
Tool names are mostly lowercase with underscores (e.g., 'ask_pipeworx', 'compare_entities', 'resolve_entity'), but there's a mix of verb-first (bulk_splits, list_subscriptions) and noun-first (data_types, get_quote) patterns. Also 'aggregates' and 'grouped_daily' both fetch bars but have different naming styles. The naming is inconsistent with no clear uniform pattern, and some names are vague like 'helpers' or 'utility-*'.
43 tools is quite heavy for a single MCP server, exceeding the typical 15-25 range for 'too many'. While the server aggregates many different domains (Polygon stocks, Pipeworx data, Polymarket, npm, etc.), the sheer number makes it overwhelming for an agent to discover and select the right tool. Many tools are meta-tools (ask_pipeworx, discover_tools) that add complexity rather than mapping to a clear domain.
The server covers a huge range of operations: stock data (retrieve, search, details), prediction markets (arbitrage, edges, research, fill risk), entity resolution, subscriptions, memory, and meta-tools. There are some gaps like no obvious tool for modifying stock data (not expected) and the Polymarket side lacks a tool for placing actual trades or managing positions. But overall the surface is quite complete for a comprehensive data/research server.