poll_memory_events

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

With no annotations, the description carries the full burden, and it delivers: it discloses the return shape, event field structure, payload limitations on automatic events, cross-process visibility, the cursor handshake, wildcard semantics, and a specific error condition for JSON-format stores. This is unusually transparent.

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 description is dense but well organized, with the core purpose front-loaded and every sentence contributing useful information. The second sentence is long and packed with caveats, but it earns its place; slightly more structure would make it a 5.

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?

There is no output schema, so the description compensates by specifying the return object and event fields, plus the error behavior on JSON stores. It covers the cursor protocol and event-type semantics well, but omitting explicit `limit` and `agent_id` semantics leaves a small completeness gap.

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 description coverage is 0%, so the description must compensate. It explains `since_seq` and `event_type` well, but `limit` and `agent_id` are left unexplained. `agent_id` can be loosely inferred from the event shape, but it is not explicitly defined, leaving a partial gap.

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 operation: poll what changed in the store since `since_seq` from the `memory_events` table, returning `{events, tip}`. It clearly distinguishes this from record-fetching tools like `get`/`recall` by framing it as an event-feed poll. The resource and verb are unambiguous.

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 description gives practical usage guidance: keep `tip` and pass it back as `since_seq`, use `event_type` "*" for all types, and tail automatic events by fetching records with `get`/`recall`. It does not explicitly compare against alternatives like `subscribe_memory_event`, but the usage context is clear enough to apply correctly.

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