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

Beyond the destructiveHint annotation, the description discloses essential operational constraints: confirm must be SEND_TEST, access checks are mandatory, and the agent must never proceed when access is blocked. It also explains MCP's conversion of emailBodyText into content.root. It doesn't detail what happens if confirm is incorrect or the full side-effect profile, but the added safety guardrails are substantial.

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 description is structured in short, imperative sentences with clear front-loading of the core action and requirements. While it contains seven sentences, each adds a distinct piece of critical information about permissions, confirm value, or content modes. It could be slightly tighter, but it avoids redundant or vague language.

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 tool with 23 parameters, no output schema, and a destructive annotation, the description provides crucial operational context such as access checks, free-tier prohibition, and content-mode options. However, it leaves many required parameters (communityId, messageId, platform, recipients) without explanation and says nothing about return values or failure modes, which is a notable gap given the tool's complexity.

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 schema description coverage at only 17%, the description carries a heavy burden to explain parameters. It adds clarity for emailLexicalContent (accepts Lexical content) and emailBodyText (converted to content.root), and implies confirm must be SEND_TEST, but the remaining 20+ parameters are left undefined in both schema and description. This is insufficient compensation for the low coverage.

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 tool sends a 'Magic Reach test message' with a specific verb, resource, and scope. The word 'test' distinguishes it from sibling tools like send_magic_reach_message and send_magic_reach_stress_test_message.

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 explicit when-to-use guidance: it requires confirm set to SEND_TEST, mandates checking business permissions first, and states FREE businesses cannot use this tool regardless of individual feature rows. It also names a specific prerequisite tool (check_business_tool_access) and tells the agent to show grace-period warnings and resubscribe links before proceeding.

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