events_wait

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's real contribution is the blocking/timeout behavior and the explicit failure shape: 'Returns timed_out=true with no events when nothing matched.' That is exactly the kind of context an agent needs before calling a long-blocking tool. It doesn't mention the 60s default timeout or that the call occupies the agent until it fires.

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 short sentences, front-loaded with the blocking behavior, then an example, then the return caveat. No filler; the only mild redundancy is that timeout_ms in the first sentence is restated contextually.

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?

An output schema exists, so return values needn't be explained, and the description does note the timed_out case. But for a 7-param blocking tool with zero schema descriptions, the unmentioned scope filters (pane_id, workspace_id, limit) and the default timeout leave real gaps an agent must guess at.

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 0%, so the description must compensate, and it only partially does: it explains since_seq (a cursor), timeout_ms, and gives example values for kinds and agent_status. Three of seven params (limit, pane_id, workspace_id) get no mention at all, leaving their filtering semantics undocumented.

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?

States a specific verb and resource ('Block until a matching event arrives') plus the key gating condition (after since_seq, or until timeout_ms). 'Block' implicitly distinguishes it from the non-blocking siblings events_recent/events_status, but those siblings are never named.

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?

The 'Typical: kinds=["pane_agent_status_changed"], agent_status=["done","blocked"]' example gives implied usage context for the common case. It never says when to use this instead of events_recent or events_status, nor when not to block, so guidance remains inferential.

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