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

Annotations declare destructiveHint=true and idempotentHint=false, and the description adds compliance context the annotations cannot: opt-ins tied to a marketing registration require evidence (source, time, page). It does not explain the destructive aspect (that a prior consent record is overwritten), which keeps it below 5.

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 short sentences, no filler, and the proof requirement — the least obvious constraint — is placed immediately after the core purpose.

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?

For a destructive, non-idempotent mutation with no output schema and a nested evidence object, the description supplies the key compliance rule an agent would otherwise miss. It omits what happens to an existing consent record on overwrite, a minor but real 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?

With 60% schema coverage and a nested proof object, the description usefully glosses the proof payload as 'source, when, the page', mapping to source, collected_at, and page_url. It leaves campaign_id, note, and the opted_out path to the schema, which documents them adequately.

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?

The description states a specific verb and resource ('Record an opt-in or opt-out') and scopes the source ('your own system (CRM, checkout, a form)'), which cleanly separates it from ingestion paths like import_opt_outs. It does not name a sibling tool, so it stops short of a 5.

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?

It implies the usage context (consent captured outside the platform) and adds one conditional rule ('An opt-in for a marketing registration needs proof'). It never says when to prefer this over import_opt_outs, list_opt_outs, or set_contact_topic, so an agent must infer the boundary.

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