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

Annotations already declare destructive=true, idempotent=true, openWorld=true, so the safety profile is covered. The description adds genuinely non-redundant behavior: it will not resend completed steps, it requires three specific scopes, and it does not call the provider API itself. It stops short of stating what happens on a non-paused campaign or whether the resume itself is reversible.

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 sentences, front-loaded with the action and effect, and each sentence carries distinct information (scope of effect, non-resend guarantee, scopes, provider boundary). The "APP:" prefix and the trailing SendGrid disclaimer are slightly awkward but cheap.

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 no explanation, and the behavioral story is solid, but for a 7-parameter mutation with 0% schema coverage and no required fields, the definition leaves the caller unable to construct a correct call. Supplying required scopes and a paused-state precondition is not enough to close that 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% across 7 parameters, so the description carries the full burden and provides nothing: the id vs campaignId relationship, the idempotencyKey, and the four external* identifiers are all unexplained. An agent cannot tell from either source which identifier is authoritative, which is a real risk given zero required parameters.

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 ("Resumes a paused outbound email campaign") plus the effect on the send engine, which implicitly separates it from launch_campaign (fresh send) and pause_campaign (the inverse). It never names a sibling explicitly, so an agent must infer the routing, but the "paused" precondition does most of the disambiguation work.

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 phrase "Resumes a paused ... campaign" gives the caller a clear precondition for use, and "Requires pause, launch, and send scopes" states a prerequisite. There is no explicit when-not guidance (e.g., what to do if the campaign is in draft or already running, or that pause_campaign is the reverse operation), so it stops short of a full routing description.

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