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

Annotations already declare a destructive, open-world, idempotent write, but the description adds real context beyond them: submissions land in a quarantine review lane, the response is a private receipt rather than publication, and routing/resolution are not guaranteed. The retry guidance (same draft_token, check tracking_token after a timeout) directly operationalizes the idempotentHint and is not derivable from the annotations alone.

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 precondition, then scope limits, then retry semantics — a sensible priority order with no filler. The negation clause ('Not public publication, emergency dispatch, guaranteed routing or resolution') is a compressed fragment, but each item carries distinct meaning.

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 covers the receipt and tracking_token return, so the description needn't describe return values. Given a two-parameter mutation with high blast-radius potential, the definition covers precondition, scope, idempotency, and timeout recovery — everything needed to invoke it correctly.

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 50% — 'confirmed' is documented but 'draft_token' has no schema description. The description compensates by tying draft_token to the prepare step and mandating reuse on retry, and by tying 'confirmed' to prior user approval of the exact preview. It stops short of stating where draft_token originates or its expiry, so it is strong but not fully compensating.

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 ('Submits to CleanApp's quarantine review lane') and immediately scopes what it is not ('Not public publication, emergency dispatch, guaranteed routing or resolution'). An agent can distinguish it from cleanapp_prepare_report and cleanapp_report_status without opening any 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 gating condition: use only after the user approves the exact preview from cleanapp_prepare_report, and it names that sibling directly. It also specifies retry behavior (reuse the same draft_token) and the post-timeout check on tracking_token, so both the entry condition and the recovery path are stated.

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