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

Goes well beyond annotations: discloses credit cost ('SPENDS CREDITS'), scope of side effects ('drafts emails... It sends nothing'), asynchronous behavior ('takes several minutes; this returns as soon as it starts'), and a hard refusal precondition. This is exactly the context annotations can't express.

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?

Five short sentences, each carrying a distinct fact (purpose, cost, side-effect boundary, latency/return semantics, refusal condition), with the purpose front-loaded. Zero 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?

No output schema, but the description compensates by explaining that the call returns immediately and that get_status surfaces the drafts later. Credit cost, refusal condition, and non-sending scope are all covered — nothing an agent needs to invoke this safely is missing.

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?

Only one parameter, and schema coverage is 100% — the schema already documents workspaceId and even points to get_status for enumeration. The description adds no syntax or format detail beyond that, so the baseline 3 applies.

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+resource ('starts a discovery and drafting run for one site') and immediately distinguishes it from the scheduled variant ('instead of waiting for the next scheduled one'). An agent can tell this apart from siblings like get_status or approve_batch without opening a schema.

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?

Gives an explicit when ('instead of waiting for the next scheduled one') and an explicit when-not with the remedy ('Refused while a batch is already waiting for approval, so deal with those first'). It also routes to get_status for observing results, covering both trigger and follow-up.

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