LaunchDistro

Plan the run

plan_submissions

Destructive

Orders the directories that are ready for this product and saves the plan to the dashboard: long review queues first, then verified dofollow, then badge listings (at most a quarter of the plan), then authority, at a pace for the domain's DR, each with why it is where it is. Submits nothing. Replaces the previous plan's unsent directories.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "plan_submissions"
  }
}

Input Schema

Name	Required	Description
`days`	No	Spread the plan over this many days, when the user names a time frame (e.g. 100 directories in 30 days). Never faster than the pace allows.
`pace`	No	Only when the user asks; otherwise the DR decides.
`count`	No	How many directories to plan.
`product`	No	The product's website or name. Leave empty for the product last worked on (list_products shows them).
`domain_dr`	No	The product domain's DR, if the user knows it.
`dofollow_only`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations flag destructiveHint=true, and the description earns credit for specifying exactly what is destroyed: the previous plan's unsent directories. "Submits nothing" also confirms no external side effects, consistent with openWorldHint=false. It omits permission requirements and the response shape, so not a 5.

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?

Front-loaded with the verb and resource, then the ranking rules, then two short constraint sentences. The first sentence packs many clauses (queue length, dofollow, badge quarter-cap, authority, DR pacing, rationale), which is dense but each clause carries real ordering 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 six optional parameters, 83% schema coverage, and no output schema, the description supplies the missing behavioral picture: deterministic ordering, the badge cap, and the destructive replacement of unsent entries. Enough to call it correctly; only return-value expectations and permissions are unaddressed.

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 83%, so most parameters are already documented, including the days/pace interplay and pace defaulting to DR. The description adds the DR-based pacing rationale but nothing new about count, product, or dofollow_only, so baseline 3 applies.

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 concrete verb and resource: it orders the ready directories and saves the plan to the dashboard. The ordering rules and the closing "Submits nothing" clearly separate it from record_submission and list_submissions, so an agent can pick it without opening a 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?

Conveys clear context: use it to build a plan, and it will not submit anything, which routes the agent away from record_submission. It also warns that the previous plan's unsent directories get replaced. It never names a sibling alternative explicitly or states when not to plan, so it stops short of a 5.

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

All LaunchDistro 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.