Simulate a campaign

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

With annotations covering read/destructive/openWorld hints, the description adds real behavioral context: required scopes (campaigns:write, luca:queue_ops), data sensitivity full_content, the Idempotency-Key requirement and safe-retry semantics, and workspace override behavior. The persistent (write) nature of the simulation is disclosed. It does not address rate limits or reuse of prior simulation results.

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?

Purpose is front-loaded in the first sentence, followed by compact metadata lines (endpoint, scopes, sensitivity, idempotency, workspace). The scope/sensitivity lines are somewhat boilerplate but each conveys operational requirements an agent needs.

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?

An output schema exists so return values need not be explained, and scope/idempotency/workspace context is covered. But for a nested-object tool with 8 undocumented body fields and 60% schema coverage, the description leaves the caller without guidance on how to shape the simulation input, which is the main complexity.

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 60%; the description adds meaning for workspaceId/workspaceSlug (override default workspace) and idempotencyKey (server generates one if omitted), which largely restates schema text. It says nothing about the body object's substantive fields (lead, eventType, sourceKind, startNodeId, replayedEnrollmentId, maxSteps), which are the core of a simulation, leaving a meaningful gap.

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: 'Run a persisted dry-run simulation' scoped to a campaign. The 'without sending messages' qualifier tells the agent what the tool does not do. It does not differentiate from siblings like luca_campaigns_simulations_list, luca_campaigns_simulations_get, or luca_campaigns_comment_simulation_suite_run.

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 implicitly signals when to use it (to dry-run a campaign before publishing), and the persistence/no-send constraint is useful. However, it gives no explicit routing against the nearby simulation siblings (list vs get vs suite_run) and no preconditions beyond scope requirements.

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