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

Annotations flag destructiveHint=true; the description explains exactly what that means — replace semantics where omitting next_steps or evidence_links clears them — which is precisely the context annotations cannot convey. It further discloses role requirements (editor/owner), optimistic concurrency (STALE_EXPERIMENT), and specific error codes with their triggering conditions.

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 purpose and the key atomicity constraint, then routed through usage alternatives and validation rules. Dense but each clause carries new information; the parenthetical error codes add length that could be compressed but not removed without losing diagnostic value.

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 an 11-parameter destructive mutation with no output schema, the description covers safeguards, role gating, status/result invariants, and sibling routing. It is silent on what the call returns and on idempotency_key behavior, which are the remaining gaps an agent might hit.

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?

With 0% schema coverage the description must carry the load, and it documents 8 of 11 parameters, including the non-obvious coupling between result and final_status and the clearing behavior of optional fields. It leaves idempotency_key unexplained and doesn't tie expected_updated_at to the STALE_EXPERIMENT behavior, so the coverage is strong but not complete.

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?

Uses a specific verb+resource ('Record how an experiment ended') and explicitly claims uniqueness: 'It is the only tool that sets result.' An agent can distinguish it from hypotize_experiment_update and hypotize_experiment_transition without opening either 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?

States the typical invocation context ('Usually called in Analyzing with final_status'), the consequence ('closes the test in the same call'), and explicitly rules out the sibling ('hypotize_experiment_transition is then not needed'), plus names the alternative for corrections ('use hypotize_experiment_update'). When-to-use and when-not-to-use are both present.

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