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

Goes well beyond the annotations: it discloses that licensee scope suppresses immediately for your organisation while emailmovers propagates database-wide within one working day and notifies other licensees, that the call is free, that suppressions:write is required, and that repeats return the same suppression. The lawful-basis and PECR corporate-subscriber default add real behavioural context an agent could not infer.

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-loads purpose, then scope effects, cost, permission, idempotency, and finally the legal caveat — a sensible ordering with little waste. It reads as one dense paragraph, and the lawful-basis/PECR sentence is long enough that the operational caveat could be split out for scanability.

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 annotations plus the description cover safety, idempotency, permissions and propagation timing. The only gap is that the optional free-text 'note' parameter and edge cases like supplying neither identifier go unmentioned.

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 67% schema coverage the schema already documents scope, record_id format and email_sha256, and the description restates the mutually exclusive identifier choice already expressed by oneOf. It still adds value by explaining the email-audience consequence of the corporate-subscriber default, though 'channel' and 'note' receive no treatment in the description.

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 ('Records an objection to direct marketing') plus the two accepted identifier forms, so an agent knows exactly what the tool does before opening the schema. The scoped-effect sentence further pins down what kind of write this is.

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?

'Call it whenever a contact objects, in any channel' gives clear triggering context, and the two scope values are explained as alternatives with different propagation. It stops short of explicitly routing away from related tools such as check_suppression for verification, so no exclusion is stated.

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