Pillars, rules and invariants

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

Annotations already declare read-only, closed-world, non-destructive behavior. The description adds useful behavioral detail: commands must be run in their declared folder relative to the tree, rules without commands require judgement, titles state what pillars reject, and commands must not be confused with proof. The phrase 'then record it' is slightly ambiguous for a read-only tool, but it can be read as guidance to record via another tool.

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 description is front-loaded and information-dense, with each sentence adding a rule or constraint. It is appropriately sized for the procedural guidance, though the branch about recording governance could be phrased more cleanly.

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 zero-parameter read-only tool with no output schema, the description covers purpose, usage, command execution, missing-governance handling, and key constraints. It does not describe the return format or structure of the governance data, but that is a minor gap given the tool's simplicity.

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?

The tool has zero parameters, so the baseline is 4. No parameter semantics are needed, and the description does not waste space restating schema details.

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 opens with a specific verb, 'Read', and enumerates the resources returned: pillars, rules including unparented ones, verification commands, and invariants. It is clear what the tool does, but it does not explicitly distinguish itself from siblings such as vivac_decide or vivac_why.

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 clearly says to read this before judging or deciding, and gives a procedure for when the tree lacks governance but project instructions define it: propose mapping, obtain approval, then record. It lacks explicit when-not guidance or named alternative tools, but the usage context is clear.

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