Skip to main content
Glama

Whimbrel MedTech Analyst

by com.whimbrelresearch
OverviewDiscussionsAdmin

Find matching signals

find_signals
Read-onlyIdempotent

Search the full monitored corpus of US medtech buying signals across years: NIH and NSF SBIR/STTR awards, federal medical R&D contracts, FDA 510(k) clearances, PMA approvals, De Novo grants, Breakthrough marketing authorizations, Humanitarian Device Exemption (HDE) approvals, ClinicalTrials.gov device trial registrations, device listings, device recalls, CDRH warning letters, device import-alert listings, and SEC funding filings. Companies whose registry name reads as non-US are left out unless include_non_us is true. Pass kind, since, new_award, phase, min_amount_usd, matching terms, and limit. Returns sourced signals newest first. Pass specialties and skill_sets in the caller's own words, such as polymer leaflets or embolic protection. The reply then orders companies by how closely those words match each company's full stored record, with matching terms shown and every line linked to its source. Pass company with them when the caller passed one company. With neither specialties nor skill_sets, the page stays newest first. Pass ask as the question in the caller's words. The reply answers it from stored records: a company file, one fact, a company list, a list ranked against their specialties, a side-by-side, or the people by role already stored.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
askNoThe question in the caller's words. The reply answers it from stored records.
kindNoOnly return this signal kind.
limitNoMaximum signals to return (default 25, max 50).
phaseNoNIH only: restrict to this program phase.
sinceNoISO date (YYYY-MM-DD); only signals on or after it. Defaults to the last 90 days.
companyNoUse with specialties or skill_sets when the caller named one company. The reply is that company's fit, in one sentence, from stored signals.
matchingNoSpace-separated terms; each must appear in the signal's summary or abstract (e.g. 'spine implant instrument'). Frame these from the firm's capabilities.
new_awardNoNIH only: first-year awards (fresh money, partners not yet settled).
skill_setsNoThe caller's skill sets, in plain words. Companies on this page are matched and ranked against these words together with specialties. Omit this when the caller did not name skill sets. At most 1000 characters are sent.
specialtiesNoThe caller's specialties, in plain words (polymer leaflets, embolic protection). Companies on this page are matched and ranked against these words. Omit this when the caller did not name specialties. At most 1000 characters are sent.
include_non_usNoKeep companies whose registry name reads as a non-US entity (a non-US legal form such as GmbH or Co., Ltd., or a non-US place name). Default false: those are left out of this US medtech search.
min_amount_usdNoOnly signals with a stated amount at or above this.
prefer_strategicsNoWith specialties or skill_sets: list large strategics (Medtronic, Boston Scientific, Abbott, J&J and similar) ahead of emerging companies with similar coverage. Default false: emerging companies come first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / prefer_strategics
      Added value: +{
+  "description": "With specialties or skill_sets: list large strategics (Medtronic, Boston Scientific, Abbott, J&J and similar) ahead of emerging companies with similar coverage. Default false: emerging companies come first.",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / kind / enum
      Previous value: -[
-  "nih_award",
-  "nsf_award",
-  "federal_contract",
-  "sbir_award",
-  "fda_clearance",
-  "fda_pma",
-  "fda_denovo",
-  "fda_breakthrough_auth",
-  "fda_hde",
-  "fda_listing",
-  "fda_recall",
-  "fda_warning_letter",
-  "fda_import_alert",
-  "fda_pma_supplement",
-  "trial_registration",
-  "funding_filing"
-]New value: +[
+  "nih_award",
+  "nsf_award",
+  "federal_contract",
+  "sbir_award",
+  "fda_clearance",
+  "fda_pma",
+  "fda_denovo",
+  "fda_breakthrough_auth",
+  "fda_hde",
+  "fda_listing",
+  "fda_recall",
+  "fda_warning_letter",
+  "fda_import_alert",
+  "fda_pma_supplement",
+  "fda_pma_original",
+  "trial_registration",
+  "funding_filing"
+]
  3. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description usefully adds behavior beyond that: default 90-day lookback, default newest-first ordering, ranking against caller-owned words, and that every line is linked to its source. It does not mention pagination or rate limits, keeping it short of a 5.

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?

It opens with the corpus scope, which is good front-loading, but the body is three dense run-on paragraphs that repeatedly restate parameter behavior already in the schema and mix the ask-mode narrative into search-mode guidance. Signal-to-word ratio is mediocre.

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 13 optional parameters and no output schema, the description carries a real explanatory burden and does address return shape ('Returns sourced signals newest first', replies as a company file, one fact, ranked list, or side-by-side). It is reasonably complete for this complexity, though the dual search/ask behavior could be disentangled more clearly.

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 coverage is 100%, so the schema already documents all 13 parameters in detail and the baseline is 3. The description mostly restates schema content (specialties, skill_sets, matching) rather than adding syntax, ranges, or interaction rules beyond what is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search the full monitored corpus of US medtech buying signals') and enumerates the source types covered, which separates it from siblings like latest_signals or who_got_funded. However, it conflates two modes (signal search and 'ask' question answering), which muddies what the tool fundamentally is.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives conditional guidance on parameters ('Pass company with them when the caller passed one company', 'With neither specialties nor skill_sets, the page stays newest first'), which implies usage. But it never says when to choose find_signals over siblings such as latest_signals, watch_space, or who_got_funded, leaving the selection decision to inference.

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

All Whimbrel MedTech Analyst toolsInspect
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