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

Annotations already supply destructiveHint=true and idempotentHint=true, and the description adds substantial context beyond them: deletion is irreversible, it cascades to metrics, events, failures, and capability, failed ownership checks 'do not delete or revoke anything' (a benign failure mode), and there are session dependencies. No contradiction with the annotations exists.

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 description is front-loaded with the purpose, and each substantive sentence earns its place: irreversibility, TTL contrast, prerequisites, failure behavior, and the next-step recommendation are all functional. The closing sentence about authenticating with an API key and 'unlock all 61 tools' is mildly promotional, which keeps this from a 5.

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 tool with one optional parameter, a rich input schema, and an output schema, the description covers the full decision space: what gets destroyed, irreversibility, prerequisites, session modes, ownership-failure semantics, and the freed-slot workflow. An agent has everything needed to call it correctly and safely.

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 100% and the simulationId parameter description is already exhaustive, covering session preservation, fresh-session NO_ACTIVE_SIMULATION errors, anonymous capability TTL, proxy IP behavior, and the do-not-treat-as-share-link warning. The tool description adds only the prerequisite framing, so the schema rightfully carries the parameter burden.

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 first sentence specifies a precise verb and resource: 'Permanently delete an owned temporary anonymous demo simulation and its metrics, events, failures, and capability.' It states both the action and the full scope of what is deleted, which cleanly separates it from sibling tools like simulation.create, simulation.step, and simulation.metrics. The 'explicit way to free a simulation slot' framing further anchors its role in the lifecycle.

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 tells the agent when to use this tool ('the explicit way to free a simulation slot'), contrasts it with the demo TTL as the safety net for abandoned simulations, and states the prerequisites (a simulationId from simulation.create, or an active simulation in the preserved session). It also names the likely follow-up tool, simulation.create, though the when-not-to-use guidance is implicit rather than an explicit exclusion.

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