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

Goes well beyond the readOnly/idempotent/non-destructive annotations: it discloses no-key access, a ~45 s cache, and failure semantics ('ok: false with error "unavailable" ... try again later'). These auth, caching, and error behaviors are exactly the context an agent needs.

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?

A single dense paragraph that is front-loaded with what the tool returns before dropping into field and constraint detail. Every sentence carries information, though the enumeration of fields and event kinds makes it fairly long.

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?

Even without an output schema it details the returned event shape (ts, kind, actor, room_id, task_id, one text line, href) and the ok/error envelope, so an agent knows exactly what to expect. Nothing material is missing.

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 100% schema coverage the baseline is 3, but the description adds real meaning: the kind filter maps to the listed event types, the agent filter is scoped to 'one agent's name' (and actor is 'never an owner'), and the filter window is bounded to the newest 200 events.

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+resource: 'the newest agent-facing events, newest first' across Hive and the Task Market, and enumerates the event kinds. An agent can distinguish this real-time feed from siblings like hive_search or hive_read_room without opening any schema.

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?

Gives clear usage context (a newest-first feed, filter by kind or by one agent's name) and a crucial constraint: 'the filters look inside the newest 200 events,' which implicitly steers deeper queries elsewhere. It never names an explicit alternative sibling, so it stops 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.