Skip to main content
Glama

propose_condition_edit

Propose a condition change (tag rename, waste %, multiplier, height, roll setup) as a pending diff the estimator accepts or rejects. Nothing changes until approval.

Instructions

PROPOSE a change to a condition instead of making it (#365): a diff — a new finish tag (rename), waste %, ×N multiplier, height_ft, roll_setup — held PENDING until the estimator accepts it from the panel. edit_condition is the wrong power for "I think this condition is wrong": a tag rename or a knob change should be a decision the estimator makes, not one they discover. Until acceptance NOTHING changes — takeoff_summary and export_report keep computing from the current values and carry the diff beside them (proposed_condition_edits), and once accepted the report is byte-for-byte what a direct edit_condition would have produced (the same write path). Only fields that differ from the current value are recorded; a proposal that changes nothing is refused, and a rename onto a tag another condition already carries is refused (two conditions on one tag would make one unreachable). One pending diff per condition — proposing again replaces the earlier one (undo_last restores it). rationale is required: the estimator accepts a reason.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
conditionYesFinish tag of an EXISTING condition, e.g. 'CPT-1'
height_ftNo
rationaleYesWhy — the schedule row, the spec section, the sheet note that decided it
waste_pctNo
finish_tagNoProposed new tag (a rename)
multiplierNo
roll_setupNoProposed roll-goods setup, or null to propose opting out

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteYes
currentYes
proposedYes
conditionYes
rationaleYes
proposal_idYes
condition_idYes
replaced_proposal_idNoPresent when this proposal replaced an earlier pending one on the same condition

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.21

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers: the diff is held PENDING until accepted, nothing changes until then, takeoff_summary and export_report keep computing current values and carry the diff as proposed_condition_edits, and acceptance is byte-for-byte identical to a direct edit_condition. It also discloses four distinct refusal/failure modes (no-op proposal, tag collision, one-pending-diff-replaces-earlier, required rationale), which is unusually complete for a mutation tool with zero annotation coverage.

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 and the edit_condition contrast are front-loaded, and each clause carries real information (pending semantics, refusals, replacement rule). It is on the dense/long side with several parentheticals and em-dash asides, so it is efficient rather than maximally tight.

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?

An output schema exists, so return values need not be described, and the description still covers pending state, the side-channel field (proposed_condition_edits), the acceptance write path, refusal conditions, and one-pending-diff/undo behavior. Nothing an agent needs to call this correctly or predict its effects is missing.

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 57%, so the description should compensate. It does list the meaningful parameter set (finish tag, waste %, multiplier, height_ft, roll_setup) and adds a semantic constraint the schema lacks: 'Only fields that differ from the current value are recorded.' Rationale's meaning is elaborated ('Why — the schedule row, the spec section, the sheet note that decided it') matching the schema description, and finish_tag is flagged as a rename. It stops short of per-field units/format detail but covers the semantics well.

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+resource ('PROPOSE a change to a condition instead of making it') and immediately contrasts it with the sibling edit_condition, so an agent can distinguish the two tools without opening a schema. The parenthetical lists the exact field classes the proposal can carry (tag rename, waste %, ×N multiplier, height_ft, roll_setup).

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?

Explicitly routes: edit_condition is 'the wrong power for "I think this condition is wrong"', and the reason a proposal should instead be a decision the estimator makes is spelled out. It also names undo_last as the recovery path and withdraw_condition_edit exists as a sibling, giving clear when/when-not framing.

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