Admin Substitute

compliance.generate_swms

Read-onlyIdempotent

Generate a site-specific SWMS (Safe Work Method Statement) compliant with WHS Regulations 2017 s.299-303 and Safe Work Australia standards. AI drafts the document with hazards, controls, PPE (with AS/NZS standards), and emergency procedures. CRITICAL: Output is an AI DRAFT only — must be reviewed and signed by a competent person before use. Requires Growth+ plan.

Input Schema

TableJSON Schema

Name	Required	Description
`trade`	Yes	Trade type (plumbing, electrical, hvac, carpentry, roofing, painting, landscaping). Required.
`startDate`	No	Planned start date (ISO 8601). Optional.
`siteAddress`	No	Site address where work will be performed. Optional.
`highRiskWork`	No	Is this high-risk construction work per WHS Regs s.291? If unsure, set to true. Optional.
`specificRisks`	No	Any specific risks already identified. Optional.
`jobDescription`	Yes	Detailed description of the work to be performed. Be specific about location, equipment, and methods. Required.
`supervisorName`	No	Name of the site supervisor. Optional.

Output Schema

TableJSON Schema

Name	Required	Description
`document`	No	Full SWMS document
`warnings`	No	Legal and compliance warnings
`requiresHumanReview`	No	Always true — human sign-off is mandatory

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is safe. The description adds valuable behavioral context: the output is an AI draft that must be reviewed by a competent person and requires a specific plan, which annotations lack.

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 three sentences, front-loaded with purpose and compliance, then content, then critical warning. No wasted words; every sentence adds essential information.

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?

Given the tool's complexity (7 parameters, output schema exists), the description is complete: it explains the regulatory basis, document contents, draft nature, and plan requirement. It doesn't detail output format, but the output schema likely covers that. Slight gap in not mentioning file format or return type.

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 description coverage is 100%, so parameters are well-documented in the schema. The description adds regulatory context (compliance details) but does not repeat or enhance parameter semantics beyond what the schema provides. Baseline score of 3 is appropriate.

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 clearly states the tool generates a site-specific SWMS compliant with WHS Regulations and Safe Work Australia standards, with explicit details about content (hazards, controls, PPE, emergency procedures). The verb 'generate' and resource 'SWMS' are specific and distinguish this from sibling tools, which are unrelated.

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?

The description provides clear context: the output is an AI draft that must be reviewed and signed, and a Growth+ plan is required. It implies when to use (for generating SWMS) but does not explicitly exclude alternatives or compare to other tools, though no direct sibling exists.

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

All Admin Substitute tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0

Disambiguation4/5

Most tools have distinct resource+action naming (e.g., leads.create, jobs.list), but some overlap exists in analytics tools (dashboard, detailed, financials) and workflow automations (process_lead vs google_ads_pipeline). Descriptions clarify purposes, so slight confusion is possible but limited.

Naming Consistency5/5

All tools follow a consistent `domain.action` pattern (e.g., leads.create, billing.status). No mixing of camelCase or snake_case. Even complex names like lifecycle.assess or scaling.readiness_score adhere to the convention.

Tool Count1/5

95 tools is far beyond typical well-scoped servers (3-15). While the server aims to cover an entire business management platform, this volume is overwhelming for an agent, making selection and memory difficult.

Completeness5/5

The tool surface is exceptionally comprehensive, covering formation, hiring, compliance, funding, leads, quotes, jobs, invoicing, payments, marketing, analytics, integrations, webhooks, workflows, and more. Almost no obvious gaps in the lifecycle of running a trade business.

Resources

Need Help?