getfund

My documents

getfund_documents

Read-only

The startup's My documents files as metadata: by default the kinds the brain reads (deck, one_pager, financials, company_registry); kind lists that one kind instead (findeks, tax_certificate, signature_circular, idr, cv and other included), each file with a download link. With applicationId it adds attach, the application's file questions in form order, each with the kind its label asks for (null for a generic or video field) and the document of that kind with a download link (null when none is stored). A link needs no sign-in and works for 5 minutes; saveAs is a safe local file name. Needs brain:read and the Autopilot plan; without My documents on this server it answers not_found.

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": "getfund_documents"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	No
`startupId`	No
`applicationId`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4/5.0

Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses that links require no sign-in and expire in 5 minutes, that `saveAs` gives a safe local file name, that the call needs brain:read plus the Autopilot plan, and that a server without My documents returns not_found. It also specifies null semantics for generic/video fields and missing documents, which is exactly the operational context an agent needs.

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 default behavior and delivery details are front-loaded and each clause carries information. It is dense and slightly awkward in places ("The startup's My documents files as metadata", "and other included"), but no sentence is padding.

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?

For a read-only, 3-parameter tool with no output schema, the description covers return shape, null cases, auth/plan requirements, link lifetime, and the not_found failure mode. Only the role of `startupId` (optional vs. implicit) is left unresolved.

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?

With 0% schema description coverage, the description carries the burden and mostly succeeds: it explains that `kind` narrows to one kind rather than the default set (naming several enum values plus "other included") and that `applicationId` adds the ordered `attach` array with per-field expected kind and matched document. The gap is `startupId`, which is never named or explained — an agent cannot tell from the text whether it defaults to the caller's own startup or must be supplied.

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?

The description concretely states the resource (the startup's "My documents" files as metadata with download links) and its two output modes: a default kind set, a single `kind`, and application `attach` questions when `applicationId` is passed. The verb is nominal ("as metadata") rather than an explicit action verb, and no sibling is named for contrast, but an agent can still tell exactly what comes back.

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?

Usage is implied through the parameter modes: default read for the brain-relevant kinds, `kind` for one specific document type, `applicationId` to also get application file questions. There is no explicit when-not guidance and no routing to alternatives such as the brain-read or export tools, so the agent must infer choice from parameters.

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

All getfund 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?