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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful context — that jobs originate from campaign launch or contact import and are meant to be polled — but says nothing about job lifecycle states, what an unknown/expired jobId returns, or how long results are retained.

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?

Two tight sentences with the purpose front-loaded and no filler. The "APP:" prefix is minor noise but costs little.

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 async-job framing is present. What is missing is the id-vs-jobId distinction and any note on job states or polling expectations, which matter for an agent recovering from a non-blocking launch.

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?

Two optional parameters (id and jobId) with 0% schema description coverage, and the description explains neither. With no required params and two near-synonymous identifiers, the agent cannot tell which one to supply or whether they are aliases — a gap the description should close.

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 (Reads) and resource (an async job), and narrows scope to jobs created by email-campaign launch or contact import. That distinguishes it from get_campaign, get_campaign_status and get_usage without naming them explicitly.

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?

"Use instead of holding the original request open" implies the polling pattern after launch_campaign or import_contacts, which is real usage guidance. But it never says when to call this versus get_campaign_status, or how often to poll, leaving the main routing decision to inference.

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