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

Beyond readOnlyHint, it discloses the fallback path (no chats shows most recent chats, only for sidebar launch) and the output norm (the card is the answer, at most one or two sentences). 'Does not mark anything read' largely restates readOnlyHint, so it adds a bit less than the rest of the 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?

The description is front-loaded with the trigger condition, then the workflow, then the fallback, and every sentence carries information. It is dense but not padded; the only near-redundant line is the read-status note.

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 a rich schema and an output schema already present, the description supplies everything else an agent needs: the trigger, prerequisite reads, the substitute-behavior rule, ordering and reason format, and the empty-chats fallback.

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 real meaning: chats go in priority order, up to 8, each with a one-line reason naming who is waiting and on what, illustrated with a concrete example. That guidance on reason quality goes beyond the schema's 'one plain sentence'.

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 states a specific job — render the catch-up card — and scopes it to the exact user intent (what needs attention/reply, to catch up). It also distinguishes itself from chats_recent/get_messages, which are named as prerequisites rather than substitutes.

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?

It gives explicit sequencing (read chats_recent and get_messages first, then always show the card instead of writing the list out) and names the one case where it is used without chats (opening from the sidebar). Alternatives and exclusions are both covered.

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