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

Annotations already establish the safe profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds genuinely useful behavior beyond that: there is no output schema, yet it discloses the return shape (conversation ids intended for get_conversation, plus per-tab counts). It does not mention pagination behavior or the limit cap, which the schema covers separately.

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?

Two sentences, front-loaded with the tool's identity ('The inbox list'), with the return-value statement placed last. The parenthetical enum lists make the first sentence dense and partially redundant with the schema, but nothing is wasted outright.

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 7 optional parameters, no required ones, and no output schema, the description covers the key things: what the filters mean in aggregate and what comes back (ids and tab counts). It is thin on sorting and the unread filter, but those are documented in the schema, so no critical gap remains for correct invocation.

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 100% and every parameter (sort, limit, search, status, unread, assignee, productId) is already documented in the schema, so the baseline is 3. The description largely paraphrases the assignee and status enums rather than adding syntax or semantics the schema lacks, and it omits the sort and unread parameters entirely.

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 concretely scopes the tool as the inbox conversation list, enumerating the exact filter dimensions (view, status tab, product, search) that define what it returns. It implicitly separates itself from get_conversation (single conversation, named as the consumer of these ids), though it never explicitly addresses the similarly-named sibling list_agent_conversations. Clear and specific, but framed as a noun phrase rather than a verb+resource statement with explicit sibling differentiation.

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 filter dimensions convey the contexts in which to use it (browsing the inbox by view/status/product/search), and it hints at the follow-up workflow by stating it returns ids for get_conversation. It gives no explicit when-not to use it and doesn't contrast with list_agent_conversations or the various search/list siblings, so the routing guidance is implicit rather than complete.

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