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

With annotations covering only read/write/idempotency hints, the description carries the load and delivers: atomic rollback behavior, the exact permission requirement and resulting INSUFFICIENT_ROLE error with required_roles, framework defaulting, status-alias coercion (Testing/Analysis), result-mapping rules, and a full error taxonomy. This is exactly the behavioral context annotations cannot express.

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 core promise (batch size, atomicity, error naming) is front-loaded in sentence one, followed by permissions and then validation rules. It is a dense single paragraph, but given the volume of error codes and lifecycle rules it is appropriately sized; a bulleted structure would have aided scanning.

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 nested-array import with no output schema, the description covers permissions, validation per status, coercion rules, and errors thoroughly enough to construct a valid call. It omits what a successful response returns (created IDs, per-row results) and the practical meaning of reusing an idempotency_key, leaving minor gaps.

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 description coverage is 0%, so the description must compensate, and it does for the highest-risk fields: scores keys must match the framework (ICE impact/confidence/ease, PIE potential/importance/ease, RICE reach/impact/confidence/effort), result/status interactions, winner_variant validation, and idempotency_key reuse. It does not cover funnel, short_idea, tags, or variant constraints, so it falls short of exhaustive.

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 precise verb and resource plus scope: 'Import up to 50 existing experiments atomically,' and immediately explains the all-or-nothing semantics. That distinguishes it from the single-record siblings, but it never explicitly names an alternative (e.g., repeated hypotize_idea_create or hypotize_experiment_update), so it stops short of full sibling differentiation.

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 description gives prerequisites (editor/owner role) and validation conditions that implicitly define when a batch will succeed, but it never states when to prefer this tool over creating experiments one at a time or over the other experiment tools in the sibling list. Usage context is implied by the word 'import' rather than argued.

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