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

Even though annotations already declare destructive=true, openWorld=true, idempotent=true, the description adds substantial context they cannot convey: required scopes (campaign:launch, email:send), the fact that delivery happens through the tenant's external email provider, that this tool does not itself call the SendGrid API or publish a web page, and that manual review holds every message until approval. That is exactly the kind of side-effect and blast-radius information an agent needs before a destructive launch.

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?

Front-loaded with the action and consequence, and nearly every sentence adds distinct information (effects, scopes, preflight re-run, external delivery, negative scope, review gate). Slightly list-like and the 'APP:' prefix plus the SendGrid/web-page denials add minor noise, but nothing is redundant.

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 and annotations cover the safety profile, so the description is strong on behavior and side effects. The significant hole is the seven undocumented input parameters on a destructive, open-world launch operation, which an agent must resolve without any prose guidance.

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% across 7 parameters, so the description carries the full burden of explaining them, and it explains none. It never mentions id vs campaignId, the idempotencyKey (only the idempotentHint annotation hints at it), or the external* correlation identifiers, leaving an agent to guess which identifier actually selects the campaign to launch.

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 (launches an outbound email campaign) and then spells out the concrete effects: copies the audience, writes the sequence as stages/senders/send window/review settings, and re-runs preflight. That detail lets an agent distinguish this from preflight_campaign (which it re-runs), from create_campaign/create_sequence (which build rather than launch), and from pause/resume/cancel siblings.

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 word 'ready' plus 're-runs preflight' establishes the precondition that a campaign must already be built and validated, and the required scopes are named. However, it never explicitly routes the agent to alternatives (e.g., 'run preflight_campaign first if not yet validated', or 'use pause_campaign to stop an in-flight send'), so exclusions are left implicit.

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