Park a node: not now

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

Annotations only state the safety profile (not read-only, not destructive, not idempotent), so the description contributes real behavioral information: the node leaves the stack and is later flagged as untouchable, and the reason string is read back verbatim under a DO NOT TOUCH NOW label. It does not say how a parked node is resumed or whether parking is reversible, which leaves one meaningful gap for a state-mutating 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 action and its effect are front-loaded in the first clause, and the remaining sentences each carry distinct information (triggers, exclusion, precondition). Slightly conversational phrasing ('something a later session is told not to touch') costs a little density but does not obscure the instruction.

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?

No output schema exists, so the description needs to convey what happens on success, and it does: the node leaves the stack and is marked do-not-touch. Combined with annotations covering the safety profile and near-complete parameter docs, an agent has what it needs to invoke this correctly; only the reverse operation (how to resume) is unaddressed.

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 both parameters are documented structurally, and the schema already covers the default-to-current-focus behavior and the reason field's rendering. The description still adds a semantic constraint beyond the schema: the id must reference a node already in the tree, otherwise vivac_add is required first.

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?

Names a specific verb and resource (park a node) and states the distinctive effect: it drops off the stack and becomes something a later session is told not to touch. It explicitly distinguishes itself from the closest sibling, vivac_pop, which is a parenthetical rather than a definitional detail.

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 explicit trigger conditions ('when the person says not now, or when work is stuck on something outside this session') and an explicit exclusion ('never as a substitute for vivac_pop on something that is simply finished'). It also supplies the precondition workflow: if the node isn't in the tree yet, file it with vivac_add first.

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