Skip to main content
Glama

site_plan

Record, update or clear where a stored plan sits in your world—origin, yaw and footprint—without re-solving it, so maps and diffs can reference it.

Instructions

Record, update or clear WHERE a stored plan stands. Nothing is re-solved.

A plan stores what to build; this stores where -- origin (x, y and optionally z, in metres, at the footprint's centre), orientation (yaw about world Z, the same convention the save stores machine facing with), and footprint (width x depth, metres). The footprint defaults to the square plan_layout budgets for the plan's largest floor, and the record keeps track of whether it was measured or derived.

Once sited: plan recalls print the siting; diff_vs_save plan=<name> adds an approximate what-stands-on-the-pad census; show_on_map at='plan:<name>' centres a map link on the origin.

The siting is a RECORD of your decision, not a constraint on the solve -- re-running the plan neither reads nor moves it, and save_as over the same name keeps it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
atNosite origin (the footprint's CENTRE): 'x,y[,z]' in metres, 'me', a factory name, 'slab:<n>' or a run id. Blank keeps the stored origin
planYes
saveNo
as_ofNopin to one world state: a sav:… token from an earlier answer
clearNo
worldNo
yaw_degNodegrees about world Z, positive +X towards +Y; omit to keep
base_revNothe plan version you read; needed to change an existing plan
footprintNo'WxD' in metres ('96' = square). Blank keeps the stored one, or derives the layout's own square if none is stored

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

No annotations exist, so the description carries full burden, and it delivers: it states the siting is a RECORD of a decision, that re-running the plan neither reads nor moves it, that save_as over the same name preserves it, and that the record tracks measured-vs-derived provenance. Missing permission/error or base_rev conflict behaviour keeps it from 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 core action, then layered into grouped rationale (what is stored, what happens once sited, the record-not-constraint caveat). Slightly long, but each paragraph carries distinct information rather than padding.

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 9-parameter mutation tool with no annotations and no output schema, the description supplies the domain model, defaults, provenance behaviour, and downstream effects an agent needs to invoke it correctly. It does not describe error or return behaviour, but nothing critical for correct invocation is absent.

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 only 56%, but the description compensates by defining the origin (footprint centre, metres), the yaw convention (about world Z, matching the save's machine-facing), and the footprint format ('WxD', defaults to the layout's square). It adds real meaning for at/yaw_deg/footprint beyond the schema, though save/as_of/world/base_rev semantics live only in the schema.

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?

Opens with a specific verb triple and resource: 'Record, update or clear WHERE a stored plan stands,' immediately scoping the tool to siting rather than solving. The 'Nothing is re-solved' line sharply distinguishes it from solve-side siblings like plan_layout and commission_plan.

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?

Explains the context of use (siting decisions), the default footprint derivation, and what becomes possible once sited (plan recalls, diff_vs_save census, show_on_map centring), naming concrete sibling tools. It stops short of explicit when-not-to-use guidance, but the 'record, not constraint' framing routes the agent well.

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