Valuein — SEC EDGAR Fundamentals & Smart-Money Data

Save Claim

save_claim

Idempotent

Persist a single falsifiable, evidence-backed CLAIM — the atomic unit of the research graph. Use this for each discrete assertion an analysis produces (e.g. 'NVDA gross margin stays above 70% through FY2026'), then compose claims into a thesis with link_claim_to_thesis. Claims are scored independently of theses, so claim accuracy is tracked as its own track record.

Pick claim_type by HOW it's judged, not what it's about: assertion = true now, checked against data; prediction = resolves at horizon_days via verifiable_condition; judgment = qualitative, not auto-scored. Use tags for the topic (financial, valuation, macro, …). Set eval_mode: 'auto' + a verifiable_condition for deterministic grading, else 'agent'/'manual'.

Tier: all paid + free tiers (sample rejected — guest has no customerId). Verifiable claims must cite evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`tags`	No	Topical labels (controlled vocab). Multi-valued; drives filtering + learning segmentation, not scoring.
`tickers`	Yes	Entities referenced (uppercased). 1 for most claims; 2+ for a comparison claim.
`evidence`	No	Evidence grounding the claim.
`direction`	Yes	Directional polarity of the claim.
`eval_mode`	No	How the outcome is resolved: auto (deterministic grade vs data via verifiable_condition), agent (an LLM judges at resolution), manual (a human marks it).	agent
`statement`	Yes	The atomic, falsifiable statement. One claim, not a paragraph.
`antecedent`	No	Scenario precondition — the claim only resolves when this holds. Null = unconditional.
`claim_type`	Yes	Epistemic type — drives scoring. assertion=true now (verified vs data); prediction=future (resolves at horizon via verifiable_condition); judgment=qualitative (not auto-scored).
`confidence`	Yes	Author confidence in [0,1]. Used as the Brier/log-loss weight when scored.
`visibility`	No	'private' (default) owner-only; 'unlisted' visible at a direct URL; 'public' surfaces on the author's profile and contributes to the claim-accuracy reputation.	private
`horizon_days`	No	Resolution horizon in days (predictions). Null for assertions/judgments.
`idempotency_key`	No	Optional client key for at-most-once semantics from a retrying agent.
`source_report_id`	No	Optional id of a report that contains the supporting analysis.
`verifiable_condition`	No	Machine-evaluable condition for eval_mode='auto'. Null otherwise.

Output Schema

TableJSON Schema

Name	Required	Description
`_meta`	Yes	Provenance envelope — data lineage for every MCP response
`claim`	Yes
`capacity`	Yes
`deduplicated`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 18, 2026

changedOutput schema / properties / _meta / properties / fundamentals_as_of / description

Previous value: -"ISO timestamp when the FINANCIAL STATEMENTS were last rebuilt. Use THIS — not `last_updated` — when telling a user how current the fundamentals are. The snapshot is republished on every weekday price refresh while the statements are carried forward unchanged, so `last_updated` can be far more recent than the numbers it sits next to."New value: +"ISO timestamp when the FINANCIAL STATEMENTS were last rebuilt in bulk. Use THIS — not `last_updated` — when telling a user how current the cross-sectional fundamentals are. The snapshot is republished on every weekday price refresh while the statements are carried forward unchanged, so `last_updated` can be far more recent than the numbers it sits next to. It is a floor for a single filer, not a ceiling: a filer with a live partition receives its filing, facts and ratios intraday (minutes after EDGAR dissemination), so an entity-scoped read may carry a filing newer than this; cross-sectional ranks (factor scores, earnings signals) refresh with the weekly bulk export."

Changed2 schema fields changedJul 25, 2026

addedOutput schema / properties / _meta / properties / fundamentals_as_of

Added value: +{
+  "description": "ISO timestamp when the FINANCIAL STATEMENTS were last rebuilt. Use THIS — not `last_updated` — when telling a user how current the fundamentals are. The snapshot is republished on every weekday price refresh while the statements are carried forward unchanged, so `last_updated` can be far more recent than the numbers it sits next to.",
+  "type": "string"
+}

addedOutput schema / properties / _meta / properties / price_as_of

Added value: +{
+  "description": "ISO timestamp when the price surfaces were last refreshed.",
+  "type": "string"
+}

Changed1 schema field changedJul 8, 2026

changedInput schema / properties / tags / items / enum

Previous value: -[
-  "financial",
-  "valuation",
-  "operational",
-  "competitive",
-  "structural",
-  "strategic",
-  "macro",
-  "behavioral",
-  "catalyst",
-  "risk",
-  "trend",
-  "comparison",
-  "liquidity",
-  "governance",
-  "guidance"
-]New value: +[
+  "financial",
+  "valuation",
+  "operational",
+  "competitive",
+  "structural",
+  "strategic",
+  "macro",
+  "behavioral",
+  "catalyst",
+  "risk",
+  "trend",
+  "comparison",
+  "causation",
+  "liquidity",
+  "governance",
+  "guidance"
+]

Changed2 schema fields changedJul 7, 2026

addedOutput schema / properties / _meta / properties / cost_usd

Added value: +{
+  "additionalProperties": false,
+  "description": "Per-call cost transparency. Omitted for subscription-only tools that have no PAYG-equivalent price.",
+  "properties": {
+    "amount_usd": {
+      "minimum": 0,
+      "type": "number"
+    },
+    "basis": {
+      "description": "payg_charge = real agent-pay charge. payg_rate_card = indicative price, not billed.",
+      "enum": [
+        "payg_charge",
+        "payg_rate_card"
+      ],
+      "type": "string"
+    },
+    "billed": {
+      "description": "true = this amount was actually charged via PAYG for this call. false = indicative PAYG-equivalent value; your plan already covers this call for free.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "amount_usd",
+    "billed",
+    "basis"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / _meta / properties / latency_ms

Added value: +{
+  "description": "Wall-clock milliseconds this tool call took, measured server-side around the handler.",
+  "minimum": 0,
+  "type": "integer"
+}

Changed1 schema field changedJul 3, 2026

addedOutput schema / properties / claim / properties / outcome_components

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {},
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Phase C resolved-metric breakdown ({evaluated, basis} from gradeClaim). Null when not yet resolved or resolved without a breakdown (manual); absent entirely on claims resolved before Phase C shipped — both mean 'no components recorded'."
+}

Changed2 schema fields changedJun 23, 2026

addedInput schema / properties / evidence / properties / source_links

Added value: +{
+  "description": "On-read enrichment of source_urls with interactive SEC viewer links.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "document_url": {
+        "description": "Direct link to the rendered primary document, or null.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "inline_viewer_url": {
+        "description": "SEC Inline-XBRL viewer on the rendered filing, or null when not iXBRL.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "sec_url": {
+        "description": "EDGAR filing-index page — always resolves.",
+        "type": "string"
+      },
+      "url": {
+        "description": "The original stored source_url (verbatim).",
+        "type": "string"
+      }
+    },
+    "required": [
+      "url",
+      "sec_url",
+      "document_url",
+      "inline_viewer_url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / claim / properties / evidence / properties / source_links

Added value: +{
+  "description": "On-read enrichment of source_urls with interactive SEC viewer links.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "document_url": {
+        "description": "Direct link to the rendered primary document, or null.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "inline_viewer_url": {
+        "description": "SEC Inline-XBRL viewer on the rendered filing, or null when not iXBRL.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "sec_url": {
+        "description": "EDGAR filing-index page — always resolves.",
+        "type": "string"
+      },
+      "url": {
+        "description": "The original stored source_url (verbatim).",
+        "type": "string"
+      }
+    },
+    "required": [
+      "url",
+      "sec_url",
+      "document_url",
+      "inline_viewer_url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed1 schema field changedJun 18, 2026
- addedOutput schema / properties / _meta / properties / pit_safe / description
```
Added value: +"true iff a zero-look-ahead point-in-time cut was applied to every returned figure"
```

Changed2 schema fields changedJun 5, 2026

changedInput schema / properties / evidence / properties / fact_ids / description

Previous value: -"fact_ids backing the claim. Cross-checked against lineage at grade time."New value: +"fact_ids backing the claim. Verified against live SEC data at save time (rejected if unresolvable)."

changedOutput schema / properties / claim / properties / evidence / properties / fact_ids / description

Previous value: -"fact_ids backing the claim. Cross-checked against lineage at grade time."New value: +"fact_ids backing the claim. Verified against live SEC data at save time (rejected if unresolvable)."

AddedMay 28, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds meaningful behavioral context beyond those: claims are scored independently of theses, fact_ids are 'Verified against live SEC data at save time (rejected if unresolvable)', and verifiable claims must cite evidence. It also explains the idempotency_key's purpose ('at-most-once semantics from a retrying agent'), which aligns with the idempotentHint annotation. The description doesn't contradict the 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 dense but well-organized: a first paragraph defining the tool's role, a second paragraph with parameter selection guidance, and a final line on tier/evidence requirements. Every sentence earns its place. It's longer than the typical description, but the tool has 14 parameters and complex semantics (claim types, eval modes, evidence requirements), so the length is justified. It could be slightly tightened, but the structure is logical and front-loaded with the core purpose.

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?

For a tool with 14 parameters, nested objects, and an output schema, the description covers the essential decision points: what a claim is, how to choose claim_type, how to choose eval_mode, what evidence is required, and tier restrictions. The output schema exists, so return values don't need explanation. The description is complete enough for an agent to correctly select and invoke this tool without opening the schema.

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 description coverage is 100%, so the baseline is 3. The description adds value above the schema by explaining the conceptual model behind parameters: claim_type is chosen by how it's judged, tags are for topic and 'drives filtering + learning segmentation, not scoring', and eval_mode determines grading. It also clarifies the relationship between horizon_days and claim_type ('prediction resolves at horizon_days via verifiable_condition'). This goes beyond the schema's per-field descriptions.

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 opens with a specific verb and resource: 'Persist a single falsifiable, evidence-backed CLAIM — the atomic unit of the research graph.' It clearly distinguishes this from related tools like save_thesis and link_claim_to_thesis by explaining that claims are composed into theses and scored independently. The example ('NVDA gross margin stays above 70% through FY2026') makes the tool's purpose concrete.

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 gives explicit when-to-use guidance: 'Use this for each discrete assertion an analysis produces... then compose claims into a thesis with link_claim_to_thesis.' It also provides decision rules for choosing claim_type ('Pick claim_type by HOW it's judged, not what it's about') and eval_mode ('Set eval_mode: 'auto' + a verifiable_condition for deterministic grading, else 'agent'/'manual''). It even notes tier restrictions ('Tier: all paid + free tiers (sample rejected — guest has no customerId)').

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

All Valuein — SEC EDGAR Fundamentals & Smart-Money Data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.