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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered structurally. The description adds real context beyond that: this writes to the board, requires standing, and demands a falsifier -- but it never says what is actually destroyed or overwritten (existing board entries?), whether the amendment takes effect immediately or awaits council review, or whether it can be reverted.

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?

Two dense sentences with the operation and its side effect front-loaded ('WRITES:') before the enumeration and the preconditions. Word-efficient, though the long comma-laden kind list is somewhat harder to parse than a bulleted form would be.

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?

With an output schema present, return values need not be explained, and the standing/rationale/falsifier requirements are covered. However, for a destructive write with a nested free-form 'proposal' object (additionalProperties, no shape), the description gives no guidance on what a valid proposal payload looks like per kind, nor what the amendment lifecycle is after submission.

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 baseline is 3, but the description earns above that by enumerating the legal values of 'kind' in prose -- necessary compensation because the schema has zero enums and only says 'from the published vocabulary'. It also glosses falsifier and rationale semantically ('why the board would be better', 'what would show the amendment was a mistake'). It does not describe the internal shape of the nested 'proposal' object per kind.

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?

The description names a specific verb ('PROPOSE AN AMENDMENT') and enumerates exactly which board artifacts can be amended (objective, open question, norm, method, reality priority, acceptance template, glossary term, revert). The leading 'WRITES:' makes it clearly distinct from read-only siblings such as read_amendment, and no sibling could be confused with it.

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?

It states a concrete gating precondition -- 'needs standing (one finding or one satisfied rung)' -- plus the required rationale and falsifier, which tells the agent exactly when it is eligible to call this. It does not name what to do instead when standing is absent (e.g., submit_finding first), so the alternative path is left implicit.

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