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

Annotations declare a mutating, idempotent operation, but the description adds behavior the annotations cannot express: optimistic concurrency with a STALE_EXPERIMENT failure, the OUTCOME_REQUIRED invariant that a closed experiment keeps non-empty actual_result and learning_summary, and role-based failure (INSUFFICIENT_ROLE with required_roles). These are exactly the constraints an agent needs before invoking a destructive update.

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?

Front-loaded with the core action, then exclusions, then concurrency and permission failure modes — every sentence carries operational weight. Slightly dense in the middle (field enumeration plus three sibling redirects), but no filler.

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 destructive, nested-payload mutation with no output schema, the description covers the safety-critical pieces: concurrency, invariants, permission failure, and sibling boundaries. The remaining gaps are partial-update semantics and the idempotency contract, which an agent may need to guess.

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% on a nested 20-field patch object, so the description must carry meaning, and it does explain the otherwise cryptic required expected_updated_at (pass the value from the last read) and which field groups are editable versus forbidden. It still doesn't spell out patch merge semantics (omitted fields unchanged) or what idempotency_key should contain, so it is strong but not 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?

States a specific verb (update), the target resource (an experiment in any status, including Ideas), and enumerates the classes of editable fields (definition fields plus outcome text such as actual_result, learning_summary, winner_variant). It also explicitly names what it does NOT change (status, result, action plan) and which siblings own those, so an agent can distinguish it from hypotize_experiment_transition and hypotize_experiment_record_outcome without opening a 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 explicit routing: use hypotize_experiment_transition to move status, hypotize_experiment_record_outcome to record the outcome, and hypotize_experiment_action_plan_set for the task list. It also supplies the precondition for calling it correctly (expected_updated_at from the last read, editor/owner role), leaving nothing to inference.

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