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

Annotations already declare destructiveHint=true and idempotentHint=false, so safety is covered structurally. The description adds real semantic context the annotations lack: these entries suppress future messaging, and there is a hard 500-number ceiling per call. It stops short of saying how duplicates or existing opt-outs are handled.

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?

One sentence, front-loaded with the action and resource, with the limit and the consequence attached. Nothing redundant.

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 single-parameter tool with annotations and no output schema, the description covers purpose, scale limit and effect. Missing only edge-case behavior (duplicates, partial failures, return counts), which is a minor gap given the tool's simplicity.

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 0%, so the description must carry the param load. It does explain the payload is phone numbers and that 500 is the per-call maximum, but leaves the required format (e.g. E.164) and handling of non-numeric entries unspecified.

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?

Names a specific verb (import) and resource (a suppression/opt-out list) and states the outcome it produces ('so people who opted out there are never texted here'). That resource framing clearly separates it from import_contacts and list_opt_outs without needing to name a sibling.

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?

The phrase 'from another provider or tool' implies the migration scenario, and the 500-per-call cap hints at batching for larger lists. But it never states when not to use it (e.g. adding a single opt-out, or reading existing opt-outs with list_opt_outs) and names no alternative.

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