Skip to main content
Glama

Pipeworx

by io.github.pipeworx-io

Data Freshness

data_freshness
Read-onlyIdempotent

MEASURES publication lag for a curated set of high-value live-data sources — how fresh is this data, how old is this number, is this feed real-time, what's the data staleness on X. Every entry is PROBED LIVE against its upstream (not read from a hardcoded table): fetches the newest available datapoint right now and reports the observed lag between that datapoint and this moment. Use before pricing or settling off a number ("can I trust this PortWatch chokepoint count as current", "how stale is Polymarket vs Kalshi order flow", "when did BLS last publish CPI"). Covers maritime chokepoint traffic (IMF PortWatch), vessel AIS positions (Digitraffic), prediction-market trade tape (Polymarket, Kalshi), global news event ingestion (GDELT), and US CPI (BLS) — pass source (forgiving match, e.g. "portwatch", "digitraffic ais", "polymarket", "kalshi", "gdelt", "cpi") or category ("maritime", "markets", "news", "economics") to scope the probe, or omit both to probe every curated source. Lag is measured at call time and can vary between calls — this tool never reports a lag it did not just observe.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceNoForgiving name match against one curated source, e.g. "portwatch", "polymarket", "kalshi", "digitraffic", "gdelt", "cpi". Omit to probe everything.
_blsKeyNoBLS registration key (gateway-injected; raises the keyless 25/day-per-IP cap that made the CPI probe intermittently unmeasurable).
categoryNoFilter to one category: maritime | markets | news | economics. Omit to probe everything.

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only and idempotent, but the description adds valuable behavioral context: it probes live upstream sources at call time, lag varies between calls, and it never reports an unobserved lag. It also notes the _blsKey parameter's effect on rate limits, going beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than ideal but front-loaded with the core purpose. Every sentence adds useful information, though the many parenthetical examples could be tightened. It remains well-organized and scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only probe tool with no output schema, the description covers the key aspects: what it measures, which sources are covered, how to scope it, and the live-probing behavior. It lacks an exact return format, but the description's mention of 'reports the observed lag' is sufficient for a tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description enhances parameter understanding by explaining the forgiving match for `source`, giving concrete examples, and clarifying that omitting parameters probes everything. This adds semantic value beyond the schema's basic type and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool measures publication lag for a curated set of live-data sources, using a specific verb+resource structure. It also distinguishes itself by emphasizing live probing rather than reading a hardcoded table, which sets it apart from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use it (e.g., 'Use before pricing or settling off a number') and gives concrete example queries. It does not explicitly mention when not to use it or name alternatives, but the context is strong enough to guide an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Pipeworx toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, especially the central data access tools like ask_pipeworx, deep_research, entity_profile, and compare_entities. However, the multiple polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread) and the similar ask_pipeworx variants could cause confusion, especially for an agent quickly scanning options.

Naming Consistency4/5

Tool names are mostly snake_case and follow a verb_noun pattern (e.g., compare_entities, search_packs, resolve_entity). Some deviations exist, such as pipeworx_feedback, polymarket_arbitrage (starting with a noun), and single-word names like forget and remember, but overall the style is readable and consistent.

Tool Count2/5

With 36 tools, the server feels overly heavy. While the broad domain (structured data across many sources) justifies a large number, the count exceeds the recommended 15–25 range, making it unwieldy for agents to navigate efficiently without extensive discovery.

Completeness4/5

The tool set covers a wide range of domains: company financials, drugs, economics, prediction markets, weather, and even MCP discovery. There are few obvious gaps given the stated purpose, though some areas like social media or international data could be added. Overall, the surface is well-rounded.

Resources