afterns

Earnings reactions and next report date

get_earnings_reactions

Read-onlyIdempotent

Show how a US stock moved the day after each of its recent earnings reports (up to the 12 most recent), whether EPS beat or missed estimates, and its next earnings date in Korea and US Eastern time. Use for questions like "엔비디아 실적 발표 언제야?", "마이크로소프트 실적 나오면 주가 어떻게 움직였어?", "Does Tesla usually drop after earnings?". Historical data only; it does not predict prices. The result is shown as an interactive card with the chart, stats, and earnings-call takeaways.

Input Schema

Name	Required	Description	Default
`lang`	No	Answer language. Use "ko" when the user writes in Korean, otherwise "en".	ko
`limit`	No	How many of the most recent reports to return (1-12)
`stock`	Yes	Ticker (NVDA) or company name in Korean or English (엔비디아, Nvidia, 구글)

Output Schema

Name	Required	Description
`call`	Yes	latest earnings-call takeaways, when available
`lang`	Yes
`next`	Yes
`as_of`	Yes
`stock`	Yes
`latest`	Yes	numbers from the most recent report
`source`	Yes
`summary`	Yes
`reactions`	Yes
`disclaimer`	Yes
`just_reported`	Yes	reported within the last 48h but results not in this data yet

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 2, 2026

changedOutput schema / properties / just_reported / description

Previous value: -"reported within the last 48h but results not in this data yet — tell the user and link the source page"New value: +"reported within the last 48h but results not in this data yet"

addedOutput schema / properties / latest

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "announced": {
+          "type": "string"
+        },
+        "eps": {
+          "description": "adjusted EPS when the company reports one, else GAAP; currency in eps_currency",
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "eps_currency": {
+          "enum": [
+            "USD",
+            "CNY",
+            "EUR",
+            "DKK"
+          ],
+          "type": "string"
+        },
+        "eps_display": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "eps_estimate": {
+          "description": "consensus EPS estimate before the report, same currency",
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "eps_estimate_display": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "eps_surprise_pct": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "eps_vs_estimate": {
+          "anyOf": [
+            {
+              "enum": [
+                "beat",
+                "miss",
+                "inline"
+              ],
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "guidance_display": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "guidance_revenue_usd": {
+          "description": "company's revenue guidance for the next quarter, when given",
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "period_end": {
+          "type": "string"
+        },
+        "revenue_display": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "revenue_usd": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "revenue_yoy_pct": {
+          "type": [
+            "number",
+            "null"
+          ]
+        }
+      },
+      "required": [
+        "announced",
+        "period_end",
+        "eps",
+        "eps_currency",
+        "eps_display",
+        "eps_estimate",
+        "eps_estimate_display",
+        "eps_vs_estimate",
+        "eps_surprise_pct",
+        "revenue_usd",
+        "revenue_display",
+        "revenue_yoy_pct",
+        "guidance_revenue_usd",
+        "guidance_display"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "numbers from the most recent report"
+}

changedOutput schema / properties / stock / properties / url / description

Previous value: -"afterns page for this stock — cite it as the source"New value: +"afterns page for this stock"

changedOutput schema / required

Previous value: -[
-  "lang",
-  "stock",
-  "next",
-  "just_reported",
-  "call",
-  "reactions",
-  "summary",
-  "as_of",
-  "source",
-  "disclaimer"
-]New value: +[
+  "lang",
+  "stock",
+  "next",
+  "just_reported",
+  "call",
+  "reactions",
+  "latest",
+  "summary",
+  "as_of",
+  "source",
+  "disclaimer"
+]

First observedNov 2, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare this as a safe, idempotent, closed-world read, so the safety profile is covered. The description goes further by disclosing the 12-report cap, the timezone convention (Korea and US Eastern), and that the response renders as an interactive card with chart, stats, and earnings-call takeaways — useful context beyond annotations, though it omits any latency or data-freshness expectations.

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?

Front-loaded with the core capability, then the sample questions, then the historical-data caveat, then the output format — a sensible ordering. The three example questions are somewhat redundant with each other, but they usefully anchor both languages.

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?

With an output schema present, the description needn't explain return values, yet it still characterizes the card presentation. For a 3-parameter read tool with full schema coverage and rich annotations, this is essentially complete; the only gap is not clarifying how it relates to the earnings-calendar and call-summary siblings.

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?

Schema description coverage is 100%, so ticker/name formats, the ko/en enum, and the 1-12 limit are all already documented. The description reinforces the 'up to 12 most recent' bound and the stock scope but adds no syntax or behavior the schema doesn't already carry, so the baseline 3 applies.

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?

States a precise verb and resource: how a US stock moved the day after each of its recent earnings reports, EPS beat/miss, and the next earnings date. The scope (up to 12 reports, US stocks, historical only) plus the concrete example questions make it immediately distinguishable from a bare calendar or call-summary tool.

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?

Sample questions (in Korean and English) show exactly the kind of query this answers, and the explicit negative constraint 'Historical data only; it does not predict prices' warns off misuse. It stops short of naming when to prefer get_earnings_calendar or get_earnings_call_summary, so routing among siblings is still inferred.

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

All afterns 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.