revise_proposal

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

With no annotations, the description carries the full burden and delivers: atomic all-or-nothing validation before any removal, the exact validation checks (sheet, scale, vertex count, height for surface_area), error reporting ('which entry and why'), undo_last restoring the prior batch exactly, and that accepted shapes are untouched. This is unusually complete behavioral disclosure.

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

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

The core action is front-loaded in the first clause, and nearly every sentence earns its place. It is dense and long with stacked parentheticals, which slightly hurts scannability but not correctness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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 no explanation, and the description fully covers the mutation's transactional semantics, validation rules, coordinate space, and role constraints. Nothing an agent needs to call this correctly is missing.

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

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%, so the description must compensate and does: it specifies verts are image px, role minimums per role type (floor_area/deduct >=3, linear/surface_area >=2, count 1), and the coordinate convention (scale 2.0, pt x 2, origin top-left, y down). This adds real meaning beyond the schema, though proposal_id is only lightly addressed.

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

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

States a precise verb+resource+scope: 'Replace EVERY still-pending shape in a proposal with a new set, as ONE journal step.' It distinguishes itself from siblings by naming what it is not (accepted shapes stay; empty list routes to withdraw_proposal) so an agent can tell it apart from propose_takeoff and withdraw_proposal.

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

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

Gives the explicit condition for use ('I re-measured and got a better batch') and the explicit exclusion ('An empty shapes list is refused — withdraw_proposal is the verb for that'), which routes the agent to the correct alternative verb by name.

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