Skip to main content
Glama

Bitcoin signals: thesis

mcw-signals-thesis
Read-onlyIdempotent

Bitcoin only, beta. The bull, base and bear cases for three horizons (scalp, short and long), as the Signals page's Thesis tab shows them. For each horizon: most_probable_arm, TSP's own most probable case (bull, base, bear or none; null when not known), with probabilities_tie true when two or more cases share the highest probability, and TSP's pick among them then its own tie-break (null when a probability is missing); dominant_case, TSP's own label: the highest-probability case with price levels (bull, base, bear or none; null when not known; the levels themselves are not published), so it can name a different case from the most probable one; the aggregate confidence; and each case's action, its probability, whether it has a signal for its direction (has_signal) and whether TSP marks it degenerate. Each horizon's inputs are judged at the moment of the answer, each series against its own cadence (judged_on[].cadence_check, and stale per input family; ETF flows by two days since their row was written). horizon_timeframes names the timeframe analyses each horizon is built from, and timeframes holds their rows, each with its own analyzed_at. Direction and probability only: no entry, target or stop is published, nor any of TSP's reasoning text. Not investment advice.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior5/5

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

Annotations already cover readOnly/idempotent/destructive=false, and the description adds substantial behavioral context beyond them: null semantics for unknown cases, `probabilities_tie` behavior, per-input staleness rules (ETF flows stale by two days since row write), cadence checks at answer time, and an explicit statement of what is NOT published (no entry, target, stop, or reasoning text).

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

Conciseness3/5

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

Purpose is front-loaded in the first sentence, but the body is a dense run-on paragraph mixing field definitions, null rules, and timing caveats without structural breaks. Because no output schema exists, the field detail does earn its place, but readability suffers.

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?

With no output schema and zero parameters, the description carries the full burden of documenting returns, and it does so comprehensively: horizons, per-case fields, aggregate confidence, tie-break logic, input freshness rules, timeframe provenance, and explicit disclaimers about unpublished data.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. Its extensive field-level prose documents the return shape rather than arguments.

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

Purpose4/5

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

States the resource (thesis: bull/base/bear cases across scalp, short and long horizons) and scope (Bitcoin only, beta) with a specific verb-like framing. It ties itself to 'the Signals page's Thesis tab,' which implicitly distinguishes it from the other Signals siblings (charts, market data, sentiment, overview, meta), but never names them explicitly.

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

Usage Guidelines2/5

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

The description explains what the data contains but not when to choose this tool over siblings like mcw-signals-overview or mcw-signals-sentiment. No when-to-use, when-not-to-use, or alternative-tool guidance is given; the tab reference is contextual framing, not usage direction.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources