Record what a decision was judged against

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

The annotations already declare this is a write (readOnlyHint=false), non-idempotent and non-destructive; the description's one added behavior is that repeating a criterion replaces its previous compliance sentence, which is genuinely useful upsert semantics. However, that replace behavior sits in slight tension with destructiveHint=false since prior compliance text is overwritten, and no permissions, error behavior, or effects on criteria not resubmitted are described.

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 short sentences with no filler, and the core action is front-loaded ahead of the replacement rule. Slightly clipped grammar ('how an existing decision met') costs a bit of clarity but nothing is wasted.

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 two-parameter tool with full schema coverage, no output schema, and annotations supplying the safety profile, the description covers purpose and the one non-obvious mutation rule. It could still say what happens when the referenced decision does not exist, but the essentials for correct invocation are present.

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% and both parameters carry rich descriptions, including the 'r12: writes stay local' format and the 'Not constraints' exclusion, so the schema already does the heavy lifting. The description adds no syntax, formatting, or meaning beyond what the schema states, which is the baseline-3 case.

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 uses a concrete verb ('Record') and a specific resource ('how an existing decision met each governing pillar/rule'), so an agent understands this attaches compliance notes to an already-existing decision rather than creating one. It does not name or contrast any sibling (e.g. vivac_decide, vivac_rules, vivac_note), so sibling differentiation is left to inference.

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?

The word 'existing' implies a prerequisite (a decision node must already be in place) and the schema's 'Decision only' note reinforces scope, but the description never states when to prefer this over vivac_decide or vivac_note, and gives no exclusions or failure conditions. Usage is implied rather than prescribed.

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