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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds genuinely new context: that the call spends workspace budget, that every attempt is metered, and that voice attempts incur synthesis and transcription costs. That cost/metering profile is not derivable from the annotations. It does not, however, describe the return value or whether the run is asynchronous.

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?

Four tight sentences, with the highest-stakes fact (budget spend) front-loaded before deployment guidance. Every sentence carries distinct information: purpose, cost, alternative, idempotency contract.

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 budget-spending mutation with no output schema and six params, the description covers the critical risks (cost, metering, safe retries) and the preview alternative. It stops short of telling the agent how to observe the run's outcome (e.g., get_simulation_run / get_simulation_run_results), which is a meaningful gap for a fire-and-forget-style start tool.

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 50% and the description's only parameter-level content is a restatement of idempotency_key semantics already documented in the schema. The undocumented params (agent_id, suite_id) are self-evident, but pinned_source's draft/published enum is left unexplained in both places, so the description does not compensate much for the coverage gap. Baseline 3 is appropriate.

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 gives a specific verb and resource ('Start a run of a simulation suite'), which cleanly separates it from preview_simulation_run, get_simulation_run, and cancel_simulation_run. An agent can identify the operation without opening the 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?

It explicitly routes to the alternative ('`preview_simulation_run` returns the estimate without starting anything'), which tells the agent exactly when NOT to call this tool. It also states that idempotency_key is required and why a retry is safe, removing any doubt about preconditions.

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