buildium-mcp

Buildium Call Endpoint

buildium_call_endpoint

Destructive

Perform write operations (POST, PUT, PATCH, DELETE) on Buildium API endpoints. Use for creating, updating, or deleting records with built-in guardrails for safe writes.

Instructions

Call any Buildium endpoint: the tool for writes.

For reads use buildium_get, which is read-only and so can be approved once.

Write guardrails apply — see buildium_health for the active mode. In the default 'fixtures' mode, every name in a create payload must carry the fixture prefix, nested ones included; a create whose payload has no name field at all is allowed against the sandbox but refused against production, since nothing on it could carry the prefix. Updates and deletes only work on records created this session, and off the sandbox so do creates under an existing record, such as a lease renewal.

Input Schema

TableJSON Schema

Name	Required	Description
`body`	No	JSON request body. Usually an object; a few endpoints, such as custom field values, take a list. buildium_describe_endpoint shows which.
`path`	Yes	Buildium API path, e.g. "/v1/vendors" or "/v1/leases/12345".
`query`	No	Query-string parameters, e.g. {"statuses": "Active"}.
`fields`	No	Keep only these top-level fields in each record, e.g. ["Id", "Name"]. Buildium records are large and carry tax IDs and addresses you may not need.
`method`	Yes	POST, PUT, PATCH or DELETE. GET also works, but buildium_get is the tool for reads.
`confirm`	No	Must be true for DELETE.
`all_pages`	No	GET only; see buildium_get.
`count_only`	No	GET only; see buildium_get.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv0.2.1Sep 24, 2026

addedInput schema / properties / all_pages / description
```
Added value: +"GET only; see buildium_get."
```

changedInput schema / properties / body / anyOf

Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  {
+    "items": {},
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / body / description

Added value: +"JSON request body. Usually an object; a few endpoints, such as custom field values, take a list. buildium_describe_endpoint shows which."

addedInput schema / properties / confirm / description
```
Added value: +"Must be true for DELETE."
```
addedInput schema / properties / count_only / description
```
Added value: +"GET only; see buildium_get."
```

addedInput schema / properties / fields / description

Added value: +"Keep only these top-level fields in each record, e.g. [\"Id\", \"Name\"]. Buildium records are large and carry tax IDs and addresses you may not need."

addedInput schema / properties / method / description

Added value: +"POST, PUT, PATCH or DELETE. GET also works, but buildium_get is the tool for reads."

addedInput schema / properties / path / description

Added value: +"Buildium API path, e.g. \"/v1/vendors\" or \"/v1/leases/12345\"."

addedInput schema / properties / query / description

Added value: +"Query-string parameters, e.g. {\"statuses\": \"Active\"}."

Changed1 schema field changedv0.2.0Sep 23, 2026
- addedInput schema / properties / count_only
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
First observedv0.1.0Sep 17, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already carry destructiveHint=true and readOnlyHint=false, but the description goes well beyond them by detailing fixture-prefix requirements for names in create payloads, session-scoped updates/deletes, and the sandbox/production differences. This materially clarifies what happens at write time without contradicting the annotations.

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 description is front-loaded with purpose and the read/write split, then packs in dense guardrail rules. It earns most of its length, though the final sentence about updates/deletes and creates under existing records is somewhat convoluted and could be clearer.

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?

Given the tool's broad scope and high parameter count, the description covers the essentials: when to use it, when not to, the active guardrail mode, fixture-prefix rules, session restrictions, and sandbox/production differences. With an output schema present and annotations carrying the destructive/read-only profile, nothing critical is missing.

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 real semantic constraints on payload values: every name in a create payload must carry the fixture prefix, nested ones included, and creates with no name field behave differently on sandbox vs. production. This supplements the schema's generic body description.

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 opens with 'Call any Buildium endpoint: the tool for writes,' which names a clear verb and resource and immediately positions it as the write-oriented counterpart to read tools. It further distinguishes itself from buildium_get by explicitly labeling that tool as read-only.

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?

It explicitly states 'For reads use buildium_get' and notes that GET also works but buildium_get is the preferred read tool. It also directs the agent to buildium_health for the active write-guardrail mode and explains sandbox-versus-production restrictions, giving concrete when-to-use guidance.

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