Pryzm Memory

Create a plan

plan_create

Creates a step-by-step plan as a draft, attached to one of the user's projects. A plan can be followed from one conversation or assistant to another.

project: the project the plan belongs to.
goal: what the plan should achieve.
phases: ordered phases, each with a title and ordered steps. Each step has a title, an instruction, a checklist of 1 to 6 verifiable criteria that define when it is done, and the expected deliverable. A plan has at most 200 steps; the free offer allows one open plan at a time. The plan stays a draft until the user approves it. Refused by the server, with nothing saved: content containing a payment card number, an API key or private key, or a password.

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": {
      "project": "<project>",
      "goal": "<goal>",
      "phases": "<phases>"
    },
    "name": "plan_create"
  }
}

Input Schema

Name	Required	Description	Default
`goal`	Yes
`phases`	Yes
`project`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 17, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations only declare the safety profile (non-read-only, non-destructive, non-idempotent); the description adds substantive behavior: the plan stays a draft pending approval, a 200-step cap, a tier-based concurrency limit, and server-side refusal of card numbers, keys, and passwords with nothing saved. Only the response shape (e.g. whether a plan id is returned) is left undisclosed.

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 in the first sentence, followed by a tight bullet decomposition of the parameters and then the limits. The final refusal sentence is dense but every clause carries distinct information; nothing is redundant.

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?

For a mutating, no-output-schema tool with 0% schema coverage, the definition covers structure, limits, lifecycle state, and failure modes. The remaining gap is the return value — with no output schema, the agent cannot tell what handle (if any) the created draft yields for later plan_status or plan_validate calls.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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 parameter meaning, and it does: it explains project, goal, and the nested phases → steps structure, including that each step has a title, instruction, a checklist of 1 to 6 verifiable criteria, and an expected deliverable. That is far beyond what the bare JSON schema conveys.

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 ('Creates a step-by-step plan as a draft'), plus the scoping fact that it is attached to one of the user's projects and portable across conversations. This lets an agent distinguish it from sibling tools such as plan_propose_amendment or plan_validate without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives real operational constraints — 200-step ceiling, one open plan at a time on the free offer, draft state until user approval — but never says when to call this versus plan_list, plan_status, or plan_propose_amendment, nor what prerequisite state must exist before creating a plan.

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

All Pryzm Memory 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?