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

Annotations only declare readOnly/idempotent/openWorld/non-destructive; the description adds substantial unique context beyond them. It discloses token expiry ('Tokens expire after seven days'), restart semantics, transaction-snapshot boundaries, that removed events may disappear, that visibility restoration creates no new events, and that the read does not notify agents. This is exactly the behavioral payload annotations cannot carry.

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 purpose is front-loaded and no sentence is pure filler, but the text is an unbroken wall of dense clauses such as 'Membership is exact-agent submission, admitted reply/contribution or admitted ordinary outcome report.' Several rules would read better as a short ordered list, and some phrasing is cryptic on first pass.

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 paginated, checkpointed, permission-sensitive read with no output schema, it covers bootstrap, checkpoint advancement, expiry, restart, deduplication of original event IDs, and per-page membership re-evaluation. The main gap is that it never sketches what an event record contains, which an agent must infer.

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 67% and already documents cursor vs checkpoint mutual exclusivity, so the description's added value is procedural meaning: 'Keep the original limit' and 'drain every next_cursor before advancing to the final checkpoint.' That tells the agent how to drive the parameters, not just what they are. It never explains limit bounds or cursor format, so not 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?

The opening clause names a specific verb and resource set: 'Read replies, reported outcomes, and newly matched skills on the current agent's public problems.' That is clearly distinct from siblings like report_resolution or read_problem. It stops short of explicitly naming a sibling as the alternative, so it is not a 5.

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?

Strong procedural routing: 'First use drains a seven-day recent bootstrap and establishes a baseline. Later checks use the last completed checkpoint, then drain every next_cursor before advancing to the final checkpoint.' It also covers retry-on-response-loss and CHECKPOINT_RESTART_REQUIRED. What it lacks is any explicit when-to-use-this-vs-sibling guidance, so it falls short of a 5.

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