AI Use Policy Draft

Draft a short AI use policy

draft_ai_use_policy

Read-onlyIdempotent

Builds a short AI use policy draft in Markdown (ten sections, about two pages) from the answers to get_policy_questions: purpose, scope, approved tools, data rules (what never goes into free or unapproved AI tools), allowed and prohibited uses, human review of AI output, approval of new tools, incident reporting and a review date. It is a fixed template filled with the answers: no AI model is called, there is no network access, and this server does not store or log the answers. Only company_name is required. Every other answer left out becomes a bracketed placeholder in the draft, and after the policy the result lists them, together with any free plan or kind of data that needs a second look (show that list to the person). Ask the person for the answers, do not invent them. Optional effective_date (YYYY-MM-DD) defaults to today (UTC). The output is a draft for internal use, not legal advice.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "company_name": "<company_name>"
    },
    "name": "draft_ai_use_policy"
  }
}

Input Schema

Name	Required	Description
`ai_tools`	No	Which AI tools does the team use or plan to use? Name the product and, if you know it, the plan.
`approver`	No	Who approves new AI tools and receives incident reports? A role or a name.
`industry`	No	What industry or kind of work is it?
`allowed_uses`	No	What may people use AI for? One use per entry.
`company_name`	Yes	What is the company's name?
`data_handled`	No	What kinds of non-public data does the team handle? The policy already covers client confidential information, personal data and credentials; add anything else.
`effective_date`	No	Date the policy takes effect, YYYY-MM-DD. Defaults to today (UTC).
`review_cadence`	No	How often will the policy be reviewed?
`prohibited_uses`	No	What is off limits beyond the standard rules? One item per entry.

Output Schema

Name	Required	Description
`disclaimer`	Yes
`placeholders`	Yes	Parts of the draft still to be filled in or checked; the same list is printed after the policy in the text content.
`effective_date`	Yes
`policy_markdown`	Yes	The policy draft alone, Markdown. The text content of the result is this draft followed by a list headed 'Still to fill in or check'.
`next_review_date`	Yes	Null when review_cadence was not given.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/idempotent/closed-world annotations, it discloses that no model is called, there is no network access, and answers are neither stored nor logged, plus that the template is fixed. It also explains what happens to omitted answers (bracketed placeholders, listed afterwards) and that the result flags free plans or sensitive data kinds. That is exactly the behavioral context annotations cannot carry.

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?

It is a single dense paragraph, but it is front-loaded with the artifact and size, then the data source, then the side effects. Every sentence carries information; the section enumeration is long but ties directly to the parameters. Slightly overstuffed for one block, hence 4 not 5.

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?

With 9 parameters, an output schema already present, and rich annotations, the description covers the remaining agent-relevant gaps: input provenance, placeholder behavior, non-storage guarantees, and the post-policy flag list. Nothing needed to invoke it correctly 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 meaning: only company_name is required, every omitted answer becomes a bracketed placeholder rather than an error, and effective_date defaults to today in UTC. The section-by-section enumeration also maps parameters to where they surface in the draft.

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 gives a specific verb and artifact ('builds a short AI use policy draft in Markdown'), pins down its shape (ten sections, about two pages) and names its input source, the answers to get_policy_questions. An agent can immediately tell this apart from the sibling question-listing tool.

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?

It clearly routes the agent: collect answers via get_policy_questions first, ask the person rather than invent answers, and show the trailing flag list to the person. It also frames the output as an internal draft, not legal advice. It stops short of stating explicit exclusions (e.g., when not to draft at all), so it lands at 4 rather than 5.

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

All AI Use Policy Draft tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?