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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: preview is trimmed to 300 characters, pagination defaults to 25/max 100, and the has_more loop semantics. Return format and preview caveat are disclosed.

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?

Front-loaded with what is listed, then triage context, then usage guidance and pagination. Dense and information-rich, though the enumeration of returned fields is long; nearly every clause earns its place.

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?

With no output schema, the description carries the return-shape burden, and it does so by enumerating fields and the 300-char preview limit plus pagination contract. Filtering by folder/channel is left to the (fully documented) schema, so nothing critical 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 the schema does not: the concrete meaning of "inbound" as replies awaiting response, the offset = offset + limit pagination formula, and the preview trimming rule. This is more than restating fields.

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+resource (list inbox conversations) and enumerates the returned content fields: counterpart, last activity, read/archive state, preview, labels, ai_category and sentiment. An agent can distinguish it from the single-thread sibling get_conversation without opening the schema.

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 explicit routing guidance: use last_message_direction "inbound" to find replies awaiting a response, and notes the preview caveat that it may be our own later message, directing the agent to get_conversation_messages to read the thread. It also spells out when to re-call (while pagination.has_more) and with what offset.

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