Skip to main content
Glama

Kaleidoscope MCP (SEC & financial data)

Bio Pipeline (point-in-time reconstruction + full trajectory)

bio_pipeline
Read-onlyIdempotent

Reconstruct a biotech company's drug pipeline at a point in time, or its full trajectory over time, with source filings cited on every fact. This is super-bio's killer capability — point-in-time pipeline reconstruction is something a frontier LLM provably cannot do without our extraction graph.

Two modes: • mode='at' (default): the company's pipeline AS OF a given date — every drug asset, its modality, current phase, targets (canonical genes), indications, and the SEC accession + verbatim snippet that established each fact. Returns the latest snapshot ≤ as_of_date. • mode='history': the full snapshot stream (per-quarter pipeline state) PLUS the resolved program_outcomes — for each drug program: first_snapshot / last_snapshot / max phase reached / final outcome (approved / advanced / acquired / discontinued).

Accepts a ticker (resolved via Atlas → CIK) or a raw CIK integer. Returns an empty assets list (NOT an error) when the company exists but has no extracted snapshot yet for the window. Resolve a target/gene name first with bio_entity_resolve if you want to cross-reference targets here against canonical genes.

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_pipeline"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo'at' = single point-in-time snapshot (default). 'history' = full snapshot stream + resolved program trajectories.at
as_of_dateNoISO date (YYYY-MM-DD). Used only in mode='at': return the latest snapshot ≤ this date. Defaults to today (i.e. the latest snapshot we have).
ticker_or_cikYesCompany ticker (e.g. 'BBIO') or raw CIK integer (e.g. 1743881).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the description's job is to add operational detail — and it does: source filings with accession and verbatim snippet are cited on every fact, 'at' resolves to the latest snapshot ≤ as_of_date, and an empty assets list is explicitly not an error. The marketing claim about what 'a frontier LLM provably cannot do' conveys no callable behavior and dilutes the otherwise substantive disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The mode bullets are front-loaded and well organized, and the empty-result and prerequisite notes are genuinely useful. However, the sentence about being 'super-bio's killer capability' and outperforming frontier LLMs is pure promotion that does not help an agent decide or call correctly, and the prose is longer than the three-parameter surface warrants.

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?

There is no output schema, and the description compensates well by naming the returned fields for both modes (drug asset, modality, phase, targets, indications, SEC accession + snippet; and for history, first/last snapshot, max phase, final outcome). It stops short of describing result size, ordering guarantees, or limits for history mode, which is the main residual gap.

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 all three parameters are already documented in the schema — including that as_of_date applies only in mode='at' and defaults to today. The description restates those semantics nearly verbatim, adding only the resolution path (ticker via Atlas → CIK) and the empty-window edge case, so it earns the baseline rather than more.

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 names a specific verb and resource ('Reconstruct a biotech company's drug pipeline') and immediately enumerates two concrete output shapes: a point-in-time snapshot and a full trajectory. It also distinguishes itself from bio_entity_resolve, which is scoped to gene/target canonicalization rather than company pipelines.

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?

Mode selection is spelled out explicitly: 'at' returns the latest snapshot ≤ as_of_date, 'history' returns the snapshot stream plus resolved program_outcomes, with the default stated. It also gives a prerequisite routing hint (use bio_entity_resolve first to cross-reference target names) and clarifies that an empty assets list is a valid result, not a failure. It does not contrast against other pipeline-adjacent siblings such as bio_target_trajectory or bio_landscape, so there is no explicit when-not guidance.

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