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

The description discloses the key side effect: 'Each call returns only unseen events and marks them seen,' which is consistent with readOnlyHint=false and idempotentHint=false. It also explains how to re-read older events via since_event_id. This adds meaningful behavioral context beyond the sparse annotations, though it does not discuss auth, rate limits, or the mark_seen=false path.

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?

Three sentences with no filler: purpose, usage schedule, and side-effect behavior are each front-loaded and distinct. Every sentence earns its place, and the most important scoping information appears first.

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 polling tool with no output schema, the description covers purpose, schedule, event types, the seen-marking side effect, and re-reading via since_event_id. It does not describe the return structure or explicitly mention that subscription updates are included, but the schema covers subscriptions and the overall behavior is sufficiently clear for correct invocation.

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 75%, so the schema already documents posts, subscriptions, and since_event_id. The description reinforces since_event_id's purpose but does not explain mark_seen, the one parameter lacking a schema description. The parameter name is self-explanatory, so the gap is minor, but the description adds little semantic 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 opens with a specific verb and resource: 'Get what's new for your posts since you last checked,' and enumerates the exact event types (matches, questions, answers, offers, counters, acceptances, declines). This clearly distinguishes it from siblings like get_post or get_messages, which retrieve individual items rather than aggregated unseen updates.

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 scheduling guidance: 'Call this on a schedule (e.g. daily) with every post you manage.' It also advises when to involve the human ('Only bother your human when something needs their decision'). However, it does not name alternatives or explicitly say when not to use this tool versus area_activity or find_matches.

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