Skip to main content
Glama

Kaleidoscope MCP (SEC & financial data)

Trial endpoint outcomes (met/missed, p-value) from SEC filings (PIT)

bio_trial_readouts
Read-onlyIdempotent

Clinical-trial endpoint outcomes for a sponsor — primary endpoint MET / MISSED / MIXED, the p-value (as stated), and the endpoint name — extracted from that filer's SEC disclosures. The actual trial RESULT per program (a tier deeper than 'assets by phase' or 'approvals'): numbers a model reading a 10-K rarely surfaces. 2,442 readouts (Ph3 1,240 / Ph2 1,126 / Ph1 65; MET 1,224 / MISSED 1,182; p-value stated on ~1/3, endpoint named on ~99%).

Inputs: ticker_or_cik (required), phase ('1'|'2'|'3'), outcome ('MET'|'MISSED'|'MIXED'), as_of (PIT — only readouts disclosed before this date), limit.

Contracts / caveats (surface these): (1) Extraction, not ground truth — outcome is classification-grade. The drug↔outcome pairing can be wrong when one disclosure window mentions multiple trials. pvalue_outcome_conflict=true marks exactly these rows — the stated p-value contradicts the outcome (MISSED with a significant p, or MET with non-significant), so the (outcome, pvalue) pairing is a likely mispair (e.g. Keytruda MISSED p<0.001). Discount the outcome↔pvalue pairing on flagged rows (~12% of rows with a p-value); the drug / phase / endpoint fields are still fine. The sentence field is the announcement text — use it to sanity-check. (2) PIT anchor is filing_date (the disclosure date), same discipline as the CRL tool — as_of gates filing_date < as_of, leak-safe. (3) Tickered universe only (argos), so delisted / private sponsors are underrepresented. (4) Filer-anchored (is_own_trial) — competitor trials narrated in a filing are excluded.

Pairs with bio_pipeline (asset → its readouts) and bio_target_base_rate (v2 — the Phase-3 misses here are what reclassify its censored programs to negatives).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ticker_or_cik": "<ticker_or_cik>"
    },
    "name": "bio_trial_readouts"
  }
}

Input Schema

NameRequiredDescriptionDefault
as_ofNoISO date YYYY-MM-DD — PIT gate; only readouts with filing_date < as_of.
limitNoMax readouts (default 50, max 200).
phaseNoTrial phase filter ('1' / '2' / '3').
outcomeNoPrimary-endpoint outcome filter (MET / MISSED / MIXED).
ticker_or_cikYesSponsor ticker (Atlas-resolved) or SEC CIK. Required.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial disclosure beyond annotations: it is extraction/classification-grade rather than ground truth, drug↔outcome mispairing can occur when a window covers multiple trials, pvalue_outcome_conflict=true flags those rows (~12% of rows with a p-value) and tells the agent to discount only the outcome↔pvalue pairing while trusting drug/phase/endpoint, plus a `sentence` field for sanity-checking. It also discloses the PIT anchor (filing_date, leak-safe), the tickered-universe limitation, and the is_own_trial filer-anchoring exclusion.

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 purpose, then a labeled Inputs line and a numbered Contracts/Caveats block, so the agent can scan rather than parse prose. It is long and dense, but nearly every clause carries decision-relevant information; the embedded corpus statistics (2,442 readouts, MET/MISSED split) are the closest thing to filler.

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, the description carries the return-value burden and does it: outcome, p-value presence (~1/3 of rows), endpoint name (~99%), the sentence field, and the conflict flag. Combined with the PIT semantics and coverage caveats, nothing an agent needs to call and interpret this tool correctly is missing.

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 coverage is 100%, so baseline is 3; the description earns extra by explaining that `as_of` is a PIT gate on filing_date (leak-safe discipline) and by giving interpretive meaning to `outcome` values (classification-grade, subject to mispairing flagged by pvalue_outcome_conflict) and `ticker_or_cik` (Atlas-resolved ticker or CIK). `limit` and `phase` get no added meaning beyond the schema.

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 resource (clinical-trial endpoint outcomes) with the exact fields returned (MET/MISSED/MIXED, stated p-value, endpoint name) and its source (filer's SEC disclosures). It explicitly positions itself relative to siblings — 'a tier deeper than assets by phase or approvals' — so an agent can distinguish it from bio_pipeline or bio_fda_approvals without opening schemas.

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?

Gives clear usage context: pull per-program trial results rather than asset/phase or approval facts, and it names the pairing workflows (bio_pipeline for asset→readouts, bio_target_base_rate for reclassifying censored programs). It does not state explicit when-not conditions or contrast directly with bio_crl_outcomes beyond noting shared PIT discipline, so it stops short of full alternative routing.

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