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

Beyond the readOnly/idempotent annotations, the description reveals non-obvious behavior: filters run before pagination, cursors belong to a live feed so a fresh first page is needed, and count values are conversation counts rather than event counts. This is high-value behavioral context.

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 dense sentences, each carrying a distinct fact: grouping model, ordering, cursor semantics, and count semantics. No filler and the most important definition 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?

The description covers the main invocation pitfalls for a read-only list tool: grouping, filter-before-pagination, live cursors, and count meaning. Given the absence of an output schema, it could still say more about what fields each conversation contains and how each tab behaves.

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?

With 0% schema coverage, the description must add parameter meaning; it explains cursor freshness and pagination ordering. However, it never details the tab enum values or how limit/pagination results are shaped, leaving part of the parameter surface to inference.

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 defines the resource as 'inbox grouped into one conversation per pull request, document, or issue activity family,' making the listing scope clear even though it lacks an explicit verb. It does not name or contrast sibling tools, so it misses the top level of 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?

'Counts are unread conversations, not events' and 'one conversation per ... activity family' imply this is the aggregated view versus event-level tools, but the description never tells the agent when to use this instead of list_inbox_conversation_events or list_notifications. Cursor and pagination guidance is operational rather than alternative-selection guidance.

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