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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description still adds real value no annotation carries: the newest-first ordering, the per-message field set, and the once-per-page `conversations` join with person, company and sync markers. It does not mention the default/max page size or whether results are capped by the `limit` ceiling, which is the remaining behavioral gap.

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?

Four tight sentences, front-loaded with the return shape and then the sync and pagination cases. The colon construction ('The tool for syncing: `unsynced_for` ...') is slightly telegraphic, but nothing is wasted.

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 correctly takes on return-shape duty and explains both the flat message feed and the grouped conversation details. An agent can call it correctly for the syncing and paging flows; only the `limit`/`direction` parameters and result-size behavior remain unexplained.

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 60%, and the description compensates well for the most consequential parameters: `unsynced_for` is explained as returning only messages newer than each conversation's mark_synced marker, and `before` is tied to the `next_before` value returned with a page. The undocumented `limit` and `direction` parameters get nothing, which keeps this from a 5.

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?

Opens with a concrete picture of the resource: a flat feed of messages across every conversation, newest first, with the fields each item carries, plus the joined `conversations` block. That distinguishes it from `list_conversations` and `read_conversation`, but it never names `search_messages`, its nearest sibling, so the boundary against searching is left implicit.

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 clear use case ('the tool for syncing' via `unsynced_for`) and the pagination recipe (`before` = next_before). It stops short of stating when not to use it or naming the alternative for keyword search, so it lands at clear context without exclusions.

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