FirmTape - SPX, ES, NQ, RTY gamma levels, 100+ symbols

Screen sessions

screen_sessions

Read-onlyIdempotent

Filter the finished SPX sessions in the FirmTape archive by their closing measurements and count them: regime at the close and at the open, zero-gamma flip crossings, direction and size of the move, net-gamma percentile, 0DTE ATM IV at the open, the calendar event, weekday and year. Returns how many sessions match, two shares over them (closed above the flip, mean absolute move) printed next to the same shares over the whole archive, and the matched days. A matched share close to the archive's share is a base rate, not a pattern. Use when: 'how often did FOMC days close in negative gamma', 'the days that closed below the flip with the percentile under 20', 'largest moves on CPI days since 2024'. Not for: one day's numbers (get_session), gamma by strike (get_gex_profile), or testing a rule with out-of-sample statistics (the Lab). Limits: counts over finished sessions' closing measurements only, no per-strike data; at most 50 sessions listed per call. Counts, not investment advice.

Input Schema

TableJSON Schema

Name	Required	Description
`iv`	No	0DTE ATM implied vol at the open: under 10%, 10-15%, 15-20%, 20% and above
`dir`	No	Direction of the open-to-close move
`dow`	No	Day of the week
`gpct`	No	Net-gamma percentile at the close: under 20, 20 to 50, 50 to 80, 80 and above
`move`	No	Size of the open-to-close move: under 0.5%, 0.5% or more, 1% or more, 2% or more
`open`	No	Regime at the open: pos = opened above the flip, neg = below
`sort`	No	Order of the sessions list: newest (default), oldest, move (largest absolute move first), gpct (highest percentile first)
`year`	No	Calendar year, e.g. 2025; a year outside the archive is dropped
`cross`	No	Flip crossings in the session: 0 = none, 1 = exactly one, 2 = two or more
`event`	No	Event the day carried: fomc (decision days), cpi, nfp (payrolls), pce, ppi, gdp, retail (retail sales), jolts, ism, claims, auctions (Treasury), fed (speeches, Beige Book), opex (expiration), vix (VIX settlement), umich, confidence, eia, halts (halt in a top name), housing (housing and durables), refunding, rebalances (index), none (no event of these kinds)
`limit`	No	How many matched sessions to list (default 20, max 50); the counts always cover every match
`regime`	No	Regime at the close: pos = closed above the zero-gamma flip, neg = below

Output Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The /screener page that shows the same result to a person
`label`	Yes	The filters in words
`shares`	Yes	The same three shares over the matched sessions and over the whole archive; a matched share close to the archive's is a base rate, not a pattern
`source`	No
`filters`	No	The filters the screener accepted; a value outside the vocabulary is dropped, not an error
`matched`	Yes	Sessions matching every filter
`summary`	Yes	One sentence carrying this answer's numbers, its trading day and its source, written to be quoted verbatim to a reader rather than paraphrased.
`archived`	Yes	Finished sessions in the archive
`screened`	Yes	Sessions whose closing measurements were available to screen
`sessions`	Yes	Matched sessions in the requested order (default newest first), at most `limit`
`truncated`	Yes	True when more sessions matched than `sessions` carries
`data_as_of`	Yes	The time this answer's data is true as of, ISO 8601 with the ET offset: a finished session's close (13:00 on an early close), the minute a ladder was read at, or the source's own build stamp. Null when the source states none.
`question_url`	No	When the filters are one of the screener's common questions, that question's own page (e.g. /screener/negative-gamma-closes), the address to cite
`server_version`	Yes	Version of the FirmTape MCP server that produced this answer

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 3, 2026

removedInput schema / properties / band

Removed value: -{
-  "description": "Whether the expected-hold band held all session",
-  "enum": [
-    "held",
-    "broke"
-  ],
-  "type": "string"
-}

addedOutput schema / properties / data_as_of

Added value: +{
+  "description": "The time this answer's data is true as of, ISO 8601 with the ET offset: a finished session's close (13:00 on an early close), the minute a ladder was read at, or the source's own build stamp. Null when the source states none.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / server_version

Added value: +{
+  "description": "Version of the FirmTape MCP server that produced this answer",
+  "type": "string"
+}

removedOutput schema / properties / sessions / items / properties / hold_band_held
```
Removed value: -{
-  "type": [
-    "boolean",
-    "null"
-  ]
-}
```

removedOutput schema / properties / shares / properties / archive / properties / band_held_pct

Removed value: -{
-  "description": "Percent of them whose expected-hold band held all session",
-  "type": [
-    "number",
-    "null"
-  ]
-}

removedOutput schema / properties / shares / properties / matched / properties / band_held_pct

Removed value: -{
-  "description": "Percent of them whose expected-hold band held all session",
-  "type": [
-    "number",
-    "null"
-  ]
-}

changedOutput schema / required

Previous value: -[
-  "summary",
-  "label",
-  "url",
-  "matched",
-  "screened",
-  "archived",
-  "shares",
-  "truncated",
-  "sessions"
-]New value: +[
+  "summary",
+  "label",
+  "url",
+  "matched",
+  "screened",
+  "archived",
+  "shares",
+  "truncated",
+  "sessions",
+  "data_as_of",
+  "server_version"
+]

AddedSep 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive behavior, so the safety profile is covered. The description adds crucial context beyond annotations: it returns counts plus two shares compared against archive-wide shares, lists at most 50 matched sessions, and warns that a matched share close to the archive's share is a base rate rather than a pattern. It also restricts counting to finished sessions' closing measurements with no per-strike data.

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 front-loads the core purpose before moving into returns, usage, exclusions, and limits. The labeled 'Use when', 'Not for', and 'Limits' sections make it easy to scan. It is slightly long and the initial filter enumeration partly repeats the schema, but every section serves a distinct 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?

Given a 12-parameter filtering tool with an output schema, the description supplies what an agent needs: counts and shares semantics, a 50-session listing cap, the fact that counts cover all matches, and clear routing to sibling tools. Output schema existence means return format details are not required, and the description still adds useful output context.

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 each of the 12 parameters already has a clear enum or format description. The description enumerates the filters in prose but adds no syntax, default, or interpretation detail beyond what the schema already provides. The baseline score of 3 is appropriate when the schema carries the parameter semantics.

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 specific verb and resource: filter finished SPX sessions in the FirmTape archive by closing measurements and count them. It distinguishes itself from siblings by naming get_session, get_gex_profile, and the Lab as alternatives for other tasks. An agent can tell exactly what this tool does and does not do without opening the schema.

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?

Provides explicit 'Use when' examples ('how often did FOMC days close in negative gamma', 'the days that closed below the flip with the percentile under 20') and an explicit 'Not for' section routing to get_session, get_gex_profile, and the Lab. This is textbook when/when-not/alternatives guidance.

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

All FirmTape - SPX, ES, NQ, RTY gamma levels, 100+ symbols 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.

Resources

Need Help?