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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful workflow behavior beyond annotations: edits invalidate the preview and require a fresh approval cycle, and costs must be surfaced for explicit approval. It stops short of describing output shape, but that is covered by the output schema.

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 short sentences, front-loaded with the purpose, then the approval requirement, then the invalidation rule. No filler.

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 annotations carry the safety profile. The workflow gate (preview → approval → launch, and re-preview after edits) is fully conveyed, leaving only the undocumented parameter meanings as a gap.

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 0% for two required params. The phrase 'saved revision' loosely maps to definitionRevision, but the description never clarifies testId, the 24-hex ID format, or what selecting a specific revision version implies. It does little to compensate for the coverage 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 (Preview) and enumerates the resource contents it surfaces: sequence, participants, costs and blockers. It is clearly distinguishable from the sibling launch_test, which it explicitly names as the subsequent action.

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?

Explicitly routes usage: present costs for approval before launch_test, and re-preview after any edit. This tells the agent both when to call it and when a prior call is invalidated.

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