Skip to main content
Glama
roynertr

COBie MCP

by roynertr

validate_cobie

Validates a COBie Excel workbook and generates an HTML report with pass/fail counts, returning status and next actions to fix errors. Use after updating COBie data to confirm compliance.

Instructions

Validate a COBie workbook and generate an HTML report.

**Read-only** (writes HTML report to disk only). Use after commit to revalidate.

**Safety:** No confirm_token on server. Client calls this to revalidate after
update_cobie/capture_installation commit.

Args:
    excel_path: Path to the COBie Excel file.

Returns:
    ValidationToolResult with summary (error/warning counts), html_path,
    status (ok|error), provenance, next_actions.

Example:
    result = validate_cobie("project.xlsx")
    # result.summary = {"total_fail": 0, "total_pass": 12, ...}
    # result.html_path = "project.validation.html"
    # result.status = "ok" | "error"
    # result.next_actions = ["Fix reported rows and re-run validate_cobie.", ...]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
excel_pathYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNook
summaryYes
html_pathYes
provenanceYes
executed_atYes
next_actionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses that the tool is read-only and that its only side effect is writing an HTML report to disk, and it notes that no confirm_token is required. It does not describe all failure modes, but the main safety and side-effect behavior is transparent.

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 well-structured with purpose, safety, args, returns, and an example. It is concise but sufficiently detailed, with no redundant or irrelevant content.

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 single input parameter and the existence of an output schema, the description provides enough context for an agent to call the tool correctly. It includes the return shape, example values, status possibilities, and suggested next actions, making it complete for practical use.

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

Parameters3/5

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

Schema coverage is 0%, so the description must compensate for the otherwise bare parameter definition. The Args section says 'Path to the COBie Excel file,' which identifies the parameter's role but adds little beyond the parameter name and the example. Adequate but minimal.

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?

Clearly states it validates a COBie workbook and generates an HTML report. The verb 'validate' and the resource 'COBie workbook' are specific, and it is distinguishable from nearby import/update/export tools.

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?

Explicitly says 'Use after commit to revalidate' and mentions it is called after update_cobie/capture_installation commits. It does not list alternative tools or when not to use it, but the timing guidance is clear enough.

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

Deploy Server

Other Tools