Sparetext

Draft a text for the user to send

draft_sms

Save a text as a draft in Sparetext instead of sending it. Nothing goes out: the user reads it in Sparetext's Messages, can change it, and taps Send. Use it when the user wants to check texts first, for a reply to look over, or when this connection may only draft. Up to 100 numbers. Returns a link to the draft.

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": {
      "to": "<to>",
      "text": "<text>"
    },
    "name": "draft_sms"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	Recipients, up to 100
`note`	No	Optional: one line for the user on why you drafted it. Shown above the draft, never sent.
`text`	Yes	The text, exactly as it should go out
`send_at`	No	Optional: when it should go once the user sends it (ISO 8601, up to 30 days ahead).

Output Schema

Name	Required	Description	Default
`url`	Yes
`draft`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 30, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Adds substantial behavior beyond the annotations: nothing is sent, the user reviews in Sparetext's Messages and taps Send, drafts are editable, and a draft link is returned. It also discloses the 100-recipient cap. The annotations only say it isn't read-only or destructive; the description explains the human-in-the-loop consequence.

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?

Four short sentences with no waste, front-loaded with the core distinction between drafting and sending. Each sentence adds a new fact: the draft destination, the review behavior, the use cases, and the return link.

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?

Complete for a 4-parameter mutation tool: annotations cover safety flags, the schema documents every parameter, and an output schema exists. The description still contributes the human-review workflow and the returned draft link, which are the key non-obvious behaviors.

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% and all four parameters are documented in the schema, so baseline is 3. The description mentions 'Up to 100 numbers,' which repeats the schema's maxItems, and adds no new syntax or meaning for 'note', 'text', or 'send_at.'

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 text as a draft in Sparetext instead of sending it') and immediately distinguishes it from the send path. An agent can tell it apart from send_sms, send_sms_batch, and delete_draft without opening the schema.

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 conditions: when the user wants to check texts first, wants a reply to look over, or when the connection may only draft. It does not explicitly name send_sms as the alternative for direct sending, but the 'instead of sending' framing implies the exclusion clearly.

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

All Sparetext 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?