Skip to main content
Glama

Check which IC Vault entries a company qualifies for (public)

ic_vault_match
Read-only

Evaluate a company profile against the Vault's eligibility predicates and get a THREE-VALUED answer per entry: 'eligible' (every stated gate is definitively met), 'ineligible' (a stated gate is definitively failed), or 'indeterminate' — which means WE CANNOT TELL FROM WHAT THE VENDOR PUBLISHES, and is a real answer, never a soft no. No auth required. Nothing is ever reported 'eligible' while any gate is unknown or unstructured: a missing profile field lands in unknown (supply it and the verdict may flip), and a gate the program states only in prose lands in manual_review (a human has to read it). A non-hit against a NAMED partner list is manual_review too, never a failure, because every published partner list in the corpus is partial. Every profile field is OPTIONAL — a partial profile is the normal case and returns more indeterminate, not an error. Accepts the same category/kind/status/evidence/freshness filters as ic_vault_list. Returns: { ok, total_considered, counts, matches[], notes }. Each match carries failed[], unknown[], manual_review[], missing_prerequisites[] and per-tier verdicts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ic_vault_match"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoSame filter as ic_vault_list.
as_ofNoYYYY-MM-DD for deadline checks. Defaults to today.
holdsNoVault entry ids you already hold — used for prerequisite checks (e.g. holding NVIDIA Inception unlocks downstream offers).
stageNoFunding stage label. Distinct from the raised amount — some programs gate on one, some on the other.
statusNoSame filter as ic_vault_list.
qualifyNoReturn only matches with this verdict. OMIT IT to see all three — asking only for 'eligible' hides the 'indeterminate' set, which is usually where the real options are.
categoryNoSame filter as ic_vault_list.
evidenceNoSame filter as ic_vault_list.
headcountNoPeople on the team. Checked against any entry that gates on team size.
domain_tagsNo'ai-native' is stricter than 'ai': the model is the product, not a feature. The corpus draws that line itself.
affiliationsNoAffiliations some programs REQUIRE (an academic grant, a 501(c)(3) discount).
jurisdictionNoISO-3166 alpha-2 of the operating entity, e.g. 'US'.
business_typesNoTypes some programs EXCLUDE. Declaring one may disqualify you from those.
cash_balance_usdNoCash on hand, USD. Orthogonal to funding raised.
has_domain_emailNoCompany-domain email. A gmail address fails these gates.
has_web_presenceNoLive website + active socials a reviewer will look at.
company_age_yearsNoYears since incorporation.
funding_raised_usdNoTotal raised, USD. 0 means bootstrapped.
has_working_productNoShipped something real, as opposed to still evaluating.
prior_participationNoVault entry ids whose program you have already taken. Distinct from being a customer.
existing_customer_ofNoVault entry ids you are already a paying customer of — for 'new customers only' gates.
partner_affiliationsNoInvestors / accelerators you are affiliated with. An EXPLICIT empty array is a statement (no affiliations ⇒ you cannot be on anyone's approved list) and fails referral gates; OMITTING the field is 'unknown' and does not.
verified_within_daysNoSame filter as ic_vault_list.
months_since_last_roundNoMonths since the most recent round CLOSED. Some programs require 'funded within 12 months' — a Series A from 3 years ago fails that while passing a stage gate.
has_institutional_backingNoSomebody institutional wrote a cheque. Says nothing about WHO — that is `partner_affiliations`.

Output Schema

NameRequiredDescriptionDefault
okNotrue when the call did what it was asked; false with `error` and `error_kind` when it did not
textNoThe tool's reply when it returns plain text instead of JSON
errorNoWhy the call failed, in a sentence a person can act on. Present only when ok is false.
resultNoThe tool's value when it returns a list or a single value instead of an object
error_kindNoMachine-readable failure class: no_token, missing_scope, forbidden, not_found, invalid_input, rate_limited or transient

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "description": "The tool's JSON result. Every field the tool's description names is present at the top level; ok, error and error_kind follow the shared envelope.",
      +  "properties": {
      +    "error": {
      +      "description": "Why the call failed, in a sentence a person can act on. Present only when ok is false."
      +    },
      +    "error_kind": {
      +      "description": "Machine-readable failure class: no_token, missing_scope, forbidden, not_found, invalid_input, rate_limited or transient"
      +    },
      +    "ok": {
      +      "description": "true when the call did what it was asked; false with `error` and `error_kind` when it did not"
      +    },
      +    "result": {
      +      "description": "The tool's value when it returns a list or a single value instead of an object"
      +    },
      +    "text": {
      +      "description": "The tool's reply when it returns plain text instead of JSON"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations cover only readOnly/openWorld; the description adds the substantive contract: no auth, three verdict values with exact meanings, missing fields routed to `unknown` (and verdicts may flip when supplied), prose gates routed to `manual_review`, and non-hits on partial partner lists treated as manual review rather than failure. That is exactly the kind of non-obvious behavior an agent cannot infer from structured fields.

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-loads the three-valued framing, which is the single most important thing to know. It is dense rather than padded, though the 'real answer, never a soft no' point is restated in the subsequent sentences and the capitalized emphasis is slightly heavy.

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?

For a 25-parameter, zero-required tool with a full schema and an output schema, the description covers the missing pieces an agent actually needs: the verdict taxonomy, why indeterminate is not failure, partial-profile tolerance, and the response envelope. Nothing required for correct invocation is absent.

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 the baseline is 3, but the description adds meaning beyond it: the blanket statement that every field is optional and that a sparse profile yields more `indeterminate` rather than an error. It also flags the return shape and the `unknown`/`manual_review` buckets that map onto parameter omissions, which helps the agent reason about what to supply.

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?

Specific verb and resource: evaluate a company profile against the Vault's eligibility predicates. It immediately distinguishes itself from ic_vault_list by framing this as a verdict engine that consumes the same filters, and it names the three-valued output upfront.

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 real operational guidance: profile fields are optional, a partial profile is the normal case, and omitting `qualify` is the intended reading because filtering to 'eligible' hides the indeterminate set. It does not explicitly say when to prefer ic_vault_list to browse versus this tool to check, but the same-filters framing implies it.

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.