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

Annotations already declare readOnlyHint=true and destructiveHint=false, which the description does not contradict. The description adds valuable behavioral context: FREE businesses are blocked regardless of feature rows, a mandatory preflight call to check_business_tool_access is required, and grace-period warnings plus verified resubscribe links must be shown. This goes beyond annotation data, though it does not detail the return format or edge-case behaviors.

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?

The first sentence is a concise, front-loaded purpose statement. The subsequent permission instructions are necessary but slightly verbose, repeating the 'before collecting inputs' idea twice. It could be tightened, but each sentence carries operational significance, making it more than just filler.

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?

Despite having six parameters and no output schema, the description does not explain what the count result looks like, how filters combine, or what a 'message selection' entails. The permission-checking context is thorough, but the core counting behavior and parameter semantics are under-specified, leaving significant gaps for an agent to use the tool 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 description coverage is 0%, and the description does not mention any of the six parameters (communityId, bucketFilters, selectedUsers, selectedBuckets, unselectedUsers, selectedMembershipTiers). It fails to provide any guidance on what these inputs mean or how they relate to the 'message selection' concept, leaving the agent to rely solely on parameter names.

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 clearly states the action ('Count recipients') and the resource ('Magic Reach message selection'), which distinguishes it from sibling tools like count_magic_reach_opt_outs (counts opt-outs) and list_magic_reach_message_recipients (lists recipients). The verb and target are specific and unambiguous.

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 description provides clear context on when to use the tool: it must only be offered after checking business permissions via check_business_tool_access, and it explicitly says never to proceed when access is blocked. However, it does not explicitly name alternative tools (e.g., use search_magic_reach_recipients for a preview or export_magic_reach_message_recipients_csv for CSV export), so it falls short of a 5.

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