Get All Unread

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description's 'Read-only' largely restates that. The genuinely additive claim is 'nothing is marked as read' — a non-obvious side-effect guarantee that distinguishes it from the mark_* / mark_all_entries_read siblings, which annotations alone would not convey. Pagination/volume behavior is left unstated.

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 short sentences, zero filler. The scope enumeration comes first and the safety guarantee second, so the most decision-relevant information is front-loaded.

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 ideally would hint at return shape (grouping by item type, pagination or volume limits). It does name the four item classes it returns, which is most of what an agent needs, and annotations carry the safety profile, but the response structure remains a minor gap.

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?

The tool takes zero parameters and the schema declares an empty properties object, so there is nothing for the description to disambiguate. Baseline of 4 applies; no parameter-level confusion is possible.

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?

Specific verb ('Get') plus resource ('every unread item') with the four included categories enumerated: inbox messages, discussion replies, announcements, activity stream items. That enumeration clearly separates it from the count-only siblings (get_unread_conversation_count, get_unread_discussion_count) and from the per-surface list tools, though none of those alternatives are named explicitly.

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?

'in one call' implies this is the aggregation shortcut instead of calling list_conversations, list_announcements, list_entries and get_activity_stream separately, which is useful implied guidance. However there is no explicit when-to-use/when-not statement and no mention of the narrower siblings an agent might prefer for a single surface.

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