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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely new behavior: the replyWindow/canReply/expiresAt 24-hour constraint, newest-first ordering, and an explicit privacy rule ('only summarize or quote them for the user who asked'). These are traits the agent could not infer from structured fields.

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?

Content is front-loaded: identity and sort order first, then payload fields, then the reply-window caveat, then privacy and workflow guidance. It is somewhat dense across several sentences, but each carries information an agent needs, so waste is minimal.

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 read-only list tool with an 8-parameter schema fully described, no output schema, and rich annotations, the description covers the remaining gaps: it enumerates the return fields (customer, preview, needsReply, assignee, replyWindow) and the reply-window semantics. Nothing needed to call it correctly is missing.

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 100%, so the baseline is 3, but the description adds meaning by explaining what needsReply actually surfaces ('conversations waiting on an answer') and clarifying that replyWindow semantics gate whether a reply is even possible. It stops short of describing search scope or pagination behavior beyond the schema.

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 ('List private direct message conversations from Instagram and Facebook Messenger for a workspace, newest first'), plus the source platforms and sort order. It is clearly distinguishable from siblings like list_conversation_messages or list_comments.

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?

Gives a concrete workflow: 'Use needsReply to find conversations waiting on an answer, then list_conversation_messages to read one,' naming the follow-up tool and the condition that selects it. It does not state when NOT to use this tool or name a competing list tool, so it stops short of the top mark.

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