Skip to main content
Glama

Plan from a description

plan
Read-only

Reads a description of the work (a prompt, tags, attachment types and sizes) into a need, then resolves it as resolve does. Use resolve when you can state the task or purpose yourself; use this when you only have the user's words. Counts as more than one call. The answer depends on these goals; have the ones that matter in hand from the plan, the repository or the user before calling: cost (optimize, max_price, budget, calls_per_user_month); depth (optimize, quality_margin, min_quality, budget, shape, needs); maker_origin (origin, origin_strict); data_region (regions); languages (languages); data_kind (needs); accounts (providers). Send them as strings in constraints; only providers and shape go at the top level.

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": {
      "providers": "<providers>"
    },
    "name": "plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoFree tags, e.g. ["vision", "read receipts", "usa", "medium"].
shapeNoAs in /v1/resolve, or auto: a team purpose's team and an escalation purpose's ladder; else a team when the reading says several models would help (ensemble_helps), an escalation when the request gives length, else single.
deviceNoThe device's memory, GPU memory and free disk in GB, for local runtimes: facts that become max_memory_gb, max_vram_gb and max_disk_gb unless constraints set them.
promptNoThe request to read. Sent only to the decision model you choose; never stored or logged.
decisionNo
providersYesRequired. Provider names, in order of preference for ties.
attachmentsNo
constraintsNoAny /v1/resolve query parameter except providers, as strings; these win over the reading. When these and the recognised tags settle the task or purpose and the budget, give needs (even empty), no tag is unrecognised, and no shape is left to the reading, the prompt is not read: the reading is empty and decision.model is local.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnly and closed-world; the description adds call accounting ('counts as more than one call'), a prerequisite protocol for goal values, and the notable fallback that settled constraints plus tags can skip reading the prompt entirely, leaving the reading empty and the model local. The cost side ('more than one call') is asserted but never quantified, and return shape is not covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and routing rule are front-loaded and efficient, but the goal enumeration is a semicolon-chained run-on that reads like compressed notes rather than prose; it is dense enough that a careful agent will need to re-parse it mid-call.

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 an 8-parameter tool with nested objects and no output schema, the description covers routing, prerequisites, constraint precedence and the prompt-skipping path. The gap is that the result of the call is only gestured at ('resolves it as `resolve` does'), with no explanation of what comes back despite there being no output schema to carry that.

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 75%, and the description still adds real meaning beyond it: it names which constraint dimensions map to which goals, states that constraints are sent as strings and 'win over the reading', and clarifies that only `providers` and `shape` live at the top level. It does not explain the mutual influence of `decision.allow_remote` beyond what the schema already says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb+resource (reads a description of the work — prompt, tags, attachment types/sizes — and resolves it) and explicitly contrasts with the `resolve` sibling on the deciding condition (user's own words vs. a task you can state yourself). The internal jargon ('a need', 'the reading', 'goals') is undefined and costs it a perfect score.

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

Usage Guidelines5/5

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

Gives a direct either/or routing rule against `resolve` and an explicit prerequisite rule ('have the ones that matter in hand ... before calling') enumerating which goals matter for cost, depth, origin, region, language, data kind and accounts. An agent knows exactly when to pick this tool and what to gather first.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources