Skip to main content
Glama
boxadm-mcp

boxadm-mcp

by shigechika

health_check

Verify the MCP server is up, confirm Box connectivity and auth, and check that admin_logs event scope is granted before running leakage detection.

Instructions

Report server version, Box connectivity/auth, and configuration.

Call this at session start (or after a tool-call timeout) to confirm the MCP is up, see which version is running, verify the Box enterprise token can be obtained (CCG) and that the admin_logs event scope is actually granted, and view the org domain allowlist used for external detection. Lightweight: one token request plus a single-row events probe — it does not scan history.

Always returns the same keys: status (healthy / degraded / error), service, version, auth_mode (ccg / oauth — the mode in effect, so an unrecognised BOX_AUTH_MODE reads as ccg, which is what the server falls back to), box_api_base, enterprise_id, auth (ok / error / missing-env / needs-login), events_accessible (bool), allowed_domains, and read_file (not-configured / ok / misconfigured: whether the opt-in read_file tool is on, from BOXADM_READ_FOLDER_IDS; misconfigured makes the status degraded). On a degraded or error result, detail carries the reason.

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": "health_check"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations present, the description carries the full burden and does so: it discloses cost and scope ('Lightweight: one token request plus a single-row events probe — it does not scan history'), enumerates the exact return keys and their value domains, explains the degraded/error `detail` field, and even documents the fallback semantics when BOX_AUTH_MODE is unrecognised. This is well beyond what any structured field supplies.

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-loaded with purpose, then the invocation trigger, then cost, then return shape — a sensible order with no filler. The long list of return keys is dense but earns its place given there is no output schema; still, it reads as a wall of backtick-heavy prose rather than a tight statement.

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 zero-parameter, no-output-schema, no-annotation tool, the description supplies everything an agent needs: what it checks, when to call it, how expensive it is, the full key set with value domains, and how degraded/error results surface reasons. No meaningful gap remains.

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?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate. The key enumeration it provides is return-value documentation rather than parameter semantics, which is useful but not what this dimension measures.

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 a specific verb-and-resource: reports server version, Box connectivity/auth, configuration, plus the checks it performs (enterprise token via CCG, admin_logs scope, domain allowlist). This is unmistakably a diagnostics tool and cannot be confused with the data-retrieval siblings like recent_admin_events or external_collaborators.

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 an explicit trigger: 'Call this at session start (or after a tool-call timeout) to confirm the MCP is up'. That is clear when-to-use guidance. It stops short of a full 5 because no alternative or when-not condition is named (e.g., no note that this is not a substitute for probing a specific failing data tool).

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