record_owner_decision

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

Annotations mark this destructive and non-idempotent, but the description goes well beyond them: private entries are stored yet EXCLUDED from get_canonical_updates, secrets auto-force private, a live human_gate is released as a side effect, and a partial failure is best-effort without undoing the canonical write. That is exactly the side-effect disclosure a destructive tool needs.

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?

Dense and front-loaded — the core write is stated first, then side effects, then the failure caveat. Slightly load-bearing with many clauses, but nearly every sentence carries a distinct behavioral fact.

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, yet the description covers the return-relevant behavior (failures are reported in the result but do not roll back), plus side effects, dedupe key, and privacy semantics. Nothing an agent needs to call this destructive multi-effect tool safely appears to be missing.

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 adds real semantics on top: it frames propagate_to as tags, explains privacy's exclusion behavior, and describes task_id's dual-record consequence and question_ref's binding rules. Only question_ref is left essentially to the schema.

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 ("Record a directive ... as a canonical decision in project_knowledge") and immediately enumerates its effects (broadcast via propagate_to, optional human_gate record). An agent can distinguish this from set_project_knowledge or remember without opening any schema.

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 clear conditions for use: owner directives, and the conditional branch for task_id ("If task_id is given, also records this as a human_gate decision"). It does not explicitly name a competing sibling or state when NOT to record a canonical decision, so it stops short of full routing guidance.

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