buildium-mcp

Buildium Download File

buildium_download_file

Read-onlyIdempotent

Download a Buildium file to your machine by supplying the file ID and destination path, automatically managing the time-limited download link.

Instructions

Download a Buildium file to this machine, handling both steps.

Buildium issues a download URL that expires after five minutes and serves the bytes from separate storage, so this cannot be done with buildium_call_endpoint.

Note this is refused when the server runs in production-readonly mode: Buildium models a download request as a POST, and that mode blocks every POST at the transport layer without exception. Reading file metadata via GET /v1/files/{id} still works.

file_id: from GET /v1/files save_to: where to write the file on this machine download_path: for a file belonging to a bill, check, or task history, that resource's own download path, e.g. "/v1/bills/123/files/456/downloadrequest". Only Buildium's seven download-request endpoints are accepted here, in every mode.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`file_id`	Yes
`save_to`	Yes
`download_path`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 17, 2026

TDQS

A5/5.0

Behavior5/5

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

Reveals the underlying two-step flow, the five-minute URL expiration, the transport-layer POST blocking in production-readonly mode, and the constraint to seven download-request endpoints. These go well beyond the annotations' read-only/idempotent hints and describe real failure modes.

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

Conciseness5/5

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

The description is organized into a short lede, a rationale paragraph, a caveat paragraph, and a parameter list. Every sentence conveys a distinct constraint or fact, with no 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?

All necessary operating constraints are present: when it works, when it is refused, why buildium_call_endpoint won't work, what the parameters mean, and which endpoints are accepted. Output schema covers return values, so nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite zero schema description coverage, the description documents each parameter meaningfully: file_id's origin, save_to's destination, and download_path's optional role with an example and endpoint restriction.

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 the action (download), target (Buildium file), destination (this machine), and disambiguates from buildium_call_endpoint by explaining why that sibling cannot do it. The two-step nature is referenced and the resource scope is clear.

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

Usage Guidelines5/5

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

Explicitly says when to use this tool instead of buildium_call_endpoint (expiring URL, separate storage), warns about production-readonly mode where it is refused, and notes that metadata reads via GET still work. This is precise routing guidance.

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