Skip to main content
Glama

AlphaAI

by io.github.makeev

Macro tape (market-wide)

alphai_macro
Read-onlyIdempotent

The market-wide macro tape from the last N hours: central-bank decisions and statements (Fed/FOMC), inflation and jobs prints, commodities, geopolitics — one call, novelty-first, so on a release day the release itself leads and the commentary follows. Use this for 'what did the Fed say', 'any macro news today', 'what's moving the whole market'. Macro rows are market-wide events and mostly carry NO tickers — that is by design; each item still carries the full AI analysis inline. Narrow with categories, or raise min_relevance to 7 to keep roughly the release-day events and drop the commentary. Syndicated reprints are collapsed by story (dedupe=false to keep all), and each collapsed item reports story_id (the story root's uid — the same key alphai_trending and the search tools report), sources_count and sources; sources_count is usually 1, a value above 1 is the signal. For what is COMING — the scheduled release calendar — use alphai_calendar. Informational and AI-generated — not investment advice.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hoursNoLook-back window in hours; default 24.
limitNoItems; capped at 20 Free/Basic, 50 Pro.
dedupeNoCollapse syndicated reprints by story (default true).
categoriesNoSubset of the macro categories; default all three.
min_relevanceNoMin AI relevance 1-10; default 4. 7+ keeps release-day events.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already mark this read-only and idempotent, and the description adds non-obvious behavior: novelty-first ordering, macro rows deliberately lacking tickers, dedupe collapsing by story, story_id being the shared key with alphai_trending/search, and sources_count > 1 as a signal. It also discloses the informational/not-investment-advice caveat. No contradiction 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.

Conciseness5/5

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

The description is long but every sentence earns its place: the core definition is front-loaded, followed by use cases, parameter tuning guidance, output conventions, and a clear pointer to the calendar sibling. Despite the density, it remains structured and readable, with no filler or tautology.

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

Completeness5/5

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

Given the tool's moderate complexity, the comprehensive schema, the output schema, and read-only annotations, the description covers everything an agent needs: scope, use cases, dedupe semantics, story_id linkage to sibling tools, relevance tuning, and the calendar alternative. Nothing material is missing.

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%, so the schema already documents all 5 parameters; the baseline is 3. The description adds genuine semantic value beyond the schema by explaining min_relevance thresholds and the dedupe behavior, and by mentioning category narrowing. It does not add much for hours/limit, but those are self-explanatory.

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 states the exact resource (market-wide macro tape over the last N hours) and enumerates the event types: central-bank decisions, inflation/jobs prints, commodities, geopolitics. It differentiates itself from siblings by emphasizing 'market-wide' and 'mostly carry NO tickers', and the companion alphai_calendar is explicitly contrasted.

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

Usage Guidelines5/5

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

It gives concrete use cases ('what did the Fed say', 'any macro news today', 'what's moving the whole market') and an explicit when-not-to-use: for scheduled upcoming events, use alphai_calendar. It also provides operational guidance like raising min_relevance to 7 to keep release-day events, which helps an agent pick parameters correctly.

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

All AlphaAI 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

A4.1/5.0
Disambiguation3/5

Multiple news feed tools (alphai_actionable_now, alphai_trending, alphai_macro, alphai_ticker_news, alphai_news_search, alphai_insider_news, and search) overlap in purpose, so an agent could pick the wrong one by name alone. The detailed descriptions clarify each tool's window, scope, and filtering, but the set still relies heavily on reading those descriptions to avoid misselection.

Naming Consistency3/5

Most tools share the alphai_ prefix and snake_case, but there is no consistent verb_noun pattern: alphai_alerts_subscribe and alphai_news_search are verb phrases while alphai_ticker_news, alphai_macro, and alphai_calendar are noun phrases. The un-prefixed connector tools search and fetch add a further deviation, making the naming readable but mixed.

Tool Count3/5

At 16 tools, the set is at the heavy end and includes several near-duplicates: alphai_news_search vs search, alphai_article vs fetch, and alphai_insider_news vs alphai_news_search(category='insider'). The domain is broad enough to justify many specialized feeds, but the redundancies make it feel padded.

Completeness4/5

The toolset covers news discovery, search, article retrieval, alerts lifecycle, macro calendar, earnings reads, ticker metadata, and pair comparisons, so agents can complete most workflows. Minor gaps remain, such as no story-level detail endpoint and no broader user-account or watchlist management beyond alerts.

Resources