DeltaSignal ATLAS-7

DeltaSignal accountless thesis create

deltasignal_thesis_create

Use this MCP beta write tool to create an accountless Thesis Monitor object protected by a one-time capability token. It stores the user-authored thesis and watch conditions in backend memory for the current runtime and returns thesis_id plus access_token once; persistent Postgres storage and x402 paid evaluation are the next implementation phase. Parameters: ticker and thesis_text are required; watch_conditions, cadence, lookback_days, output_mode, and provenance_required are optional. Behavior: non-trading write operation; it creates one in-memory thesis record with a fresh capability token, has no destructive side effects outside that requested object, does not call DeltaSignal evidence routes, does not execute wallet settlement, and refuses buy, sell, hold, target-price, allocation, or order instructions. Use it after thesis readiness when the user wants to start a lightweight MCP/x402 thesis-monitor flow without traditional accounts.

Input Schema

TableJSON Schema

Name	Required	Description
`ticker`	Yes	Required issuer ticker. Examples: MSTR, RIOT, MARA, COIN.
`cadence`	No	Optional monitoring cadence.
`output_mode`	No	Optional response mode.
`thesis_text`	Yes	Required user-authored thesis text.
`lookback_days`	No	Optional monitoring lookback window in days.
`watch_conditions`	No	Optional structured watch conditions extracted from the thesis.
`provenance_required`	No	Whether source dates, route status, and evidence provenance are required before evidence-backed evaluation.

Output Schema

TableJSON Schema

Name	Required	Description
`data`	Yes	Accountless thesis creation response. The access_token is returned once and must be kept by the client; the server stores only its hash.
`provenance`	Yes	Traceability information for the MCP tool response.
`mcp_summary`	Yes	Concise high-signal summary of the tool response. Maximum 140 characters.
`usage_metadata`	No	Performance and estimated cost metadata for this MCP tool call.
`suggested_follow_ups`	Yes	Concrete next MCP calls an agent can run to continue the workflow.

Schema Changelog

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

Changed4 schema fields changedJun 9, 2026

removedOutput schema / properties / data / properties / evidence_sections

Removed value: -{
-  "description": "Company-report section availability records. States include available, soft_miss, not_requested, failed_advisory, and failed_closed.",
-  "items": {
-    "additionalProperties": true,
-    "description": "Evidence section availability record.",
-    "type": "object"
-  },
-  "type": "array"
-}

removedOutput schema / properties / data / properties / issuer_evidence_envelope

Removed value: -{
-  "additionalProperties": true,
-  "description": "Company-report evidence envelope with parser-stable sections, availability states, SPECTRA metadata, and non-advice boundary.",
-  "type": "object"
-}

removedOutput schema / properties / data / properties / publication_audit_block

Removed value: -{
-  "additionalProperties": true,
-  "description": "Compact audit block for report publication, including route, evidence hash, section availability summary, SPECTRA state, and daily-change drilldown reference.",
-  "type": "object"
-}

removedOutput schema / properties / data / properties / spectra_metadata

Removed value: -{
-  "additionalProperties": true,
-  "description": "Promoted SPECTRA metadata for company reports, including latest point dates, row counts, current read, risk tier, charge level, and source date bounds when available.",
-  "type": "object"
-}

Changed4 schema fields changedJun 8, 2026

addedOutput schema / properties / data / properties / evidence_sections

Added value: +{
+  "description": "Company-report section availability records. States include available, soft_miss, not_requested, failed_advisory, and failed_closed.",
+  "items": {
+    "additionalProperties": true,
+    "description": "Evidence section availability record.",
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / data / properties / issuer_evidence_envelope

Added value: +{
+  "additionalProperties": true,
+  "description": "Company-report evidence envelope with parser-stable sections, availability states, SPECTRA metadata, and non-advice boundary.",
+  "type": "object"
+}

addedOutput schema / properties / data / properties / publication_audit_block

Added value: +{
+  "additionalProperties": true,
+  "description": "Compact audit block for report publication, including route, evidence hash, section availability summary, SPECTRA state, and daily-change drilldown reference.",
+  "type": "object"
+}

addedOutput schema / properties / data / properties / spectra_metadata

Added value: +{
+  "additionalProperties": true,
+  "description": "Promoted SPECTRA metadata for company reports, including latest point dates, row counts, current read, risk tier, charge level, and source date bounds when available.",
+  "type": "object"
+}

AddedMay 27, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only indicate non-readonly, non-destructive, non-idempotent flags. The description adds extensive behavioral detail: one-time capability token, in-memory storage for current runtime, returns thesis_id plus access_token once, no destructive side effects, no calls to evidence routes, no wallet settlement, and refusal of trading instructions. This goes far beyond annotations.

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 well-structured with clear sections for behavior and parameters, and the first sentence states the primary purpose. It is somewhat long but every sentence provides valuable context (beta status, token semantics, non-trading behavior). Minor redundancy with schema (e.g., listing required parameters) prevents a 5.

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 presence of a full input schema and output schema, the description completes the picture with beta status, storage model, return values, next-phase limitations, and relationship to readiness flow. It is fully sufficient for an agent to select and invoke this tool correctly.

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

Parameters3/5

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

The input schema covers all 7 parameters with detailed descriptions, giving 100% schema coverage. The description adds little beyond what the schema already says—it simply lists required vs optional params. Baseline 3 is appropriate because the schema carries the semantic burden.

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's function with a specific verb and resource: 'create an accountless Thesis Monitor object'. It distinguishes itself from sibling tools by being the only create tool for thesis monitors, and explicitly differentiates from read-only tools by calling itself a 'beta write tool'.

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?

The description provides explicit usage context: 'Use it after thesis readiness when the user wants to start a lightweight MCP/x402 thesis-monitor flow without traditional accounts.' It also clarifies limitations (persistent storage is next phase) and what the tool refuses to do, giving clear when-to-use/when-not-to-use guidance.

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

All DeltaSignal ATLAS-7 tools Inspect

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

B3.1/5.0

Disambiguation2/5

Significant overlap exists between atlas7_* and deltasignal_* tools for the same concepts (covenant stress, readiness, peer ranking, morning brief, pressure board), and composite workflows coexist with their low-level components. The descriptions are detailed but the sheer number of similar-scope tools makes misselection likely.

Naming Consistency4/5

Most tools follow a consistent lower_snake_case pattern with a domain prefix (atlas7_, deltasignal_, strategix_). Verb-first names (generate_, resolve_, search_) and noun-only names (alpha_opportunities, readiness) are both used, but the convention is predictable enough to navigate.

Tool Count1/5

With 81 tools, the surface is far beyond the 25–50 range considered excessive. Many tools are composites, natural-language variants, or near-duplicates that could be consolidated, creating an extreme mismatch for typical MCP server scope.

Completeness4/5

The tool surface is extensive, covering fundamentals, covenant stress, alpha screening, peer ranking, daily changes, briefs, historical ATLAS data, TripCode resolution, perp factors, synthetic ETF audit, and StrategiX rendering. Minor gaps exist (watchlist persistence, thesis lifecycle), but core research workflows are well covered.

Resources

Need Help?