OrgLines

Save prompt

save_prompt

Save a reusable AI prompt / template to the caller's prompt library. Provide a 'title'; optional 'body', 'category' and 'tags'. Additive and low-risk. A reusable lead reply template is just a prompt saved with category 'lead-reply' (retrieve them via list_prompts category='lead-reply') — no separate template store is needed. CONFIRMATION: this tool runs immediately when the caller asks for it — it writes only their own record, and they can undo it from this same surface, so the request is taken as the instruction. You get an ordinary result, not a plan_token. Everything destructive, outbound or financial still proposes and waits.

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": {
      "title": "<title>"
    },
    "name": "save_prompt"
  }
}

Input Schema

Name	Required	Description	Default
`body`	No
`tags`	No
`title`	Yes
`category`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing that the write is additive, low-risk, scoped to the caller's own record, and undoable from the same surface. It also explains the confirmation model explicitly — the tool runs immediately rather than returning a plan_token, unlike destructive, outbound, or financial tools — which is exactly the behavior an agent needs to decide whether to just call it.

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?

Purpose is front-loaded, followed by parameters, behavior, and the confirmation note in a logical order. The CONFIRMATION paragraph is slightly overlong and partly restates the earlier 'additive and low-risk' claim about writing only the caller's own record.

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?

Covers purpose, usage routing, mutation safety, undo path, and confirmation semantics for a 4-parameter tool with no output schema. The remaining gap is what the returned 'ordinary result' contains — notably whether a prompt identifier comes back for later retrieval via get_prompt.

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 0%, so the description must carry the burden; it names all four parameters and marks which are optional, and gives category real semantic meaning through the 'lead-reply' example. However, it adds no format guidance for 'body' or 'tags' (free-form strings vs. controlled vocabulary) or for title length constraints, leaving real semantic gaps.

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 — 'Save a reusable AI prompt / template to the caller's prompt library' — and clarifies that a 'template' is not a separate entity but a prompt with category 'lead-reply'. That clarification alone separates it from siblings like list_prompts and get_prompt.

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 clear context for use (saving reusable prompts, including lead-reply templates) and names the retrieval counterpart, list_prompts with category='lead-reply'. It does not state any exclusion, such as when a one-off prompt should not be saved, so it falls short of full when/when-not coverage.

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

All OrgLines 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?