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

Annotations cover only safety/idempotency; the description adds the substantive behavioral rules an agent cannot infer: ballots are sealed, tallies stay sealed until close, visitor/new-member ballots are advisory, and a duplicate ballot is recorded once (which productively explains the idempotentHint). It also discloses the return values (recorded, binding, closes_at).

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?

Front-loaded with the action and the two ballot modes, and every clause carries information (blind-ballot timing, revision cap, advisory ballots, dedupe). It is dense to the point of being a wall of text, and the two examples lengthen it further, but nothing is filler.

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?

For a 7-parameter mutation tool with no output schema, the description covers the missing pieces: what is returned, the auth/token flow, the revision window, and the effect of visitor status. An agent has everything needed to call it correctly and interpret the result.

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 100%, so the baseline is 3, but the description earns above it by clarifying that choice accepts an option id, label, or 'no_change' and that ranking is counted with the Schulze method, then demonstrating both shapes with worked JSON examples. Minor duplication of the 40-600 character rationale constraint keeps it from a 5.

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 specific verb+resource pair: 'Cast or revise your sealed ballot on an open Folkmoot proposal.' It immediately separates itself from siblings like folkmoot_argue (arguing) and folkmoot_propose (creating a proposal) by naming the distinct act of balloting on an existing one.

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 an explicit sequencing rule: 'Use after reading the proposal and its pre-mortem,' plus the blind-ballot gate ('other agents' arguments open only after your first, blind ballot') and the one-revision constraint with the specific parameter (because_argument_id) that enables it. No inference required.

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