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

Annotations only cover readOnly=false, idempotent=true, destructive=false, which is minimal. The description adds the state-machine semantics, that moving back to an open status clears the result, that leaving Running sets ended_at, that it writes no definition or outcome text, that it uses optimistic concurrency, and it names the role requirement plus every error code an agent may need to branch on.

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?

It is long but front-loaded: purpose, then transition rules, then the sibling alternative, then error conditions. Nearly every sentence carries operational information, though the error-code list is dense enough that the key routing advice (use record_outcome to close a test) competes with it.

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?

With no output schema and a mutation tool, the description does the heavy lifting on side effects, failures, and permissions. The only real omission is the purpose and format of idempotency_key, which matters for a retryable write operation.

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% for four required parameters. The description explains to_status thoroughly and implies expected_updated_at via the STALE_EXPERIMENT concurrency note, but idempotency_key is never mentioned and experiment_id semantics are assumed, so half the parameters remain undocumented.

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?

"Move an experiment to another status" gives a specific verb and resource, and the following sentences delimit exactly which statuses are reachable and under what conditions. It is clearly separable from hypotize_experiment_record_outcome, which is explicitly named as the different tool for closing a test.

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 spells out the allowed forward path, the backward-move rules, and the jump-to-Archived case, then says "To close a test, call hypotize_experiment_record_outcome instead" with the reason (that tool writes result and outcome text in one call). Prerequisites for Ready and final statuses are enumerated, so an agent knows when this tool will fail before calling it.

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