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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, so the safety profile is covered. The description adds genuinely non-obvious behavior: 'Simulation sends nothing and uses current facts, not predicted behavior,' plus the expectedRevision concurrency requirement and that identity comes from the connected account.

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?

Dense but front-loaded: purpose first, then action groups with their parameters, then the simulation caveat, then the guide resource. It is a long run-on sentence with heavy parenthetical nesting, which costs readability, but nearly every clause carries actionable information.

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 nine-action tool with no output schema and a free-form payload, the description covers action inventory, required parameters per action, simulation semantics, and points to the socialloop://guides/email-campaigns resource. It omits return shapes and pagination details for list/history, but the guide resource and read-only annotations cover most of the 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 coverage is only 50% and payload is an open free-form object, so the schema alone cannot guide the agent. The description compensates by mapping each action to its expected payload keys (flowId, cursor, exact email, status, memberId, targetVersion, targetStepId, enrollmentIds), which is substantial added meaning.

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 concrete verb (inspect) and resource (email sequences) and enumerates the nine actions it exposes, so an agent knows exactly what surface is covered. It does not explicitly contrast itself with mutation siblings like edit_email_sequence or activate_email_sequence, relying on the read-only name/annotations for that separation.

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 per-action parameter breakdown (flowId/expectedRevision for preview-family, memberId for simulate, targetVersion/targetStepId/enrollmentIds for previewMigration) effectively routes the agent to the right action. However, it never states when NOT to use this tool or names alternatives such as edit_email_sequence, edit_email_campaign, or inspect_email_experiment.

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