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

Adds substantial behavior beyond the readOnly/destructive/openWorld annotations: redacted messages are excluded, specific fields are withheld (raw mail, HTML, provider identifiers, delivery errors, staff email), the traversal is live rather than a snapshot, features.manage permission is required, and it carries a prompt-injection warning about public-written text.

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?

Dense and front-loaded: the resource and scope come first, then returns, then cursor semantics, then permissions and the safety note. Nearly every sentence earns its place, though the live-traversal explanation runs a bit long.

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?

No output schema exists, so the description must explain returns, and it does: plain text and quoted text, with explicit exclusions. Combined with the permission requirement and traversal caveat, an agent has everything needed to call it 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?

With schema coverage at 50%, the schema documents account_id and conversation_id but leaves limit and the nested cursor object unexplained. The description compensates partially by explaining cursor semantics (follow unchanged; restart without it), but adds nothing for limit, so it only partly fills the gap.

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 (Read) plus the exact resource and its scope: a conversation's inbound messages, sent/failed replies, private notes and system events in ingestion order. This precisely distinguishes it from sibling get_inbox_conversation (single conversation metadata) and list_inbox_conversations (conversation list).

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?

Provides context on how to traverse (follow next_cursor unchanged; restart without a cursor after concurrent activity settles for a current overview), which is genuine usage guidance. However, it never names an alternative sibling or an explicit when-not-to-use condition, so tool selection is only implied.

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