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

Annotations already flag destructiveHint=true and idempotentHint=false, so the safety profile is known. The description adds real context beyond that: removing a suppression re-consents the contact for messaging, that permission is required, and adds/removes should be user-confirmed. It does not disclose whether adds are deduplicated, what list returns, or pagination behavior, keeping it out of the top band.

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?

Three clauses in one dense line, front-loaded with the scope ('Who must not be messaged') before the mechanics and the confirmation rule last. Every clause carries information. The semicolon-chained fragments read as terse shorthand and cost a little readability.

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 9-parameter destructive mutation tool with no output schema, the description covers the selection logic, the mutation semantics, and the human-approval requirement. The remaining gap is the list mode's return shape and paging expectations, which the schema hints at (limit 1-500, default 100) but does not fully substitute for an absent output schema.

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 limit, search, source, phone, emails, and phones. The description adds the channel×action matrix — which container parameter applies to which action — which is genuinely useful. However, the singular 'email' parameter is undocumented in both schema and description, leaving its role (single add? list filter?) ambiguous, so the description does not fully compensate.

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?

Opens with a crisp scope statement ('Who must not be messaged') followed by the two channels and their real-world meaning (unsubscribed/bounced addresses, numbers that texted STOP), then enumerates the three actions. An agent immediately knows this is the suppression-list management tool and no sibling overlaps. It loses a point only for the telegraphic, fragment-style phrasing rather than a clean verb+resource sentence.

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?

Explicitly maps each action to its input shape (add via emails[]/phones[], remove via phone) and adds an operational rule: removals re-consent the contact and require their permission, and both adds and removes must be confirmed with the user. There is no alternative sibling to route to, so the absence of exclusions is not a gap. Usage guidance is clear, though nothing covers when to prefer list over search or how to page results.

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