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

Annotations already declare readOnly, idempotent and non-destructive, so the safety bar is met structurally. The description adds real behavioral context beyond them: the required `agents:read` scope, the conditional inclusion of transcripts/recordings/conversation evidence only under `recordings:read`, and that results are paginated over attempts.

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?

Three tight sentences: content first, pagination scope second, permissions last. No filler, and the most decision-relevant information (what you get back) is front-loaded.

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, the description correctly takes on the burden of describing return contents and permission-gated fields, which it does well. It stops short of covering cursor/limit behavior details or failure modes, but nothing essential for a correct call is 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 only 20% (just organization_id documented), so the description carries most of the burden. "Paginated over attempts" does clarify the scope of limit/cursor, which is genuine added meaning, but run_id, agent_id, limit and cursor formats or defaults are never explained.

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 and resource and enumerates what the run payload contains (status, attempts, per-scenario verdicts, assertion results, recognition facts, transcripts). It is clear on its own, but it does not distinguish itself from the sibling get_simulation_run_results, whose name suggests overlapping content, leaving a routing ambiguity an agent must resolve elsewhere.

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?

Usage is implied by the read-only framing and the required permission scopes, and the conditional recordings:read note hints at when extra data appears. However, there is no explicit when-to-use versus get_simulation_run_results, preview_simulation_run, or start_simulation_run, and no stated prerequisites beyond scopes.

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