Catch up on what the user missed

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

The description explains the non-idempotent behavior of moving the mark and the consequence of losing an answer (use since:'previous'), which goes beyond annotations. It also clarifies budget_tokens and cursor usage. Annotations (readOnlyHint true, destructiveHint false) are consistent, and the description adds meaningful behavioral detail without contradiction.

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 a single run-on sentence with heavy jargon ('the mark moves first', 'a lost answer is since: previous'). It is concise in length but not well-structured or front-loaded; the core purpose is somewhat buried. The cryptic phrasing reduces readability despite the compact size.

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?

For a tool with six optional parameters and non-trivial behavior (mark movement, pagination, token budget), the description covers the essential operational details: sections, account narrowing, cursor handling, and the token limit. The output schema exists to handle return values. It lacks error handling or edge cases, but overall it is sufficiently complete for an advanced tool.

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?

Despite 100% schema description coverage, the description enriches parameter understanding: it explains 'since' options, the mark movement, and the meaning of 'more.cursor'. It also lists the sections returned, which aligns with the include parameter even though terminology differs slightly (e.g., 'mentions' vs 'addressed'). This adds value beyond the schema.

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 clear purpose: fetching what the user missed across all accounts, listing sections like waiting, mentions, calls, people, groups, stories. It distinguishes from siblings by focusing on aggregated missed content, though it does not explicitly name alternatives. The title reinforces this, so it is not a tautology.

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 some usage context, such as using account_id to narrow to one account and mentioning get_status for names, plus the mark movement behavior and cursor pagination. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or prerequisites. The guidance is implicit rather than direct.

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