Retrieve bounded event history with pagination and pending-only filtering to track human input events.
Read bounded event history. Discovery is delayed; agent push is unsupported.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| after_seq | No | ||
| pending_only | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=true, destructive=false, openWorld=false, so safety is covered. The description earns credit for adding genuinely non-obvious behavior: discovery is delayed and there is no push channel, meaning the caller must re-poll rather than expect notifications. That is context the annotations cannot express.
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?
Two short sentences, front-loaded with the core verb and resource, then the polling caveat. Nothing is padded, though "bounded" is an ambiguous word that costs more confusion than it saves.
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?
No output schema exists and all three parameters are undocumented, so the description should compensate but does not: it never says what an event record contains, how the sequence cursor advances, or how pending_only interacts with human_event_ack. For a paginated read tool this leaves the agent guessing at the call protocol.
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%: limit, after_seq, and pending_only have no descriptions, types aside. The description says "bounded" but never explains that limit caps the batch, that after_seq is a pagination cursor, or that pending_only filters unacknowledged events — the three facts an agent most needs to call this correctly.
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?
"Read bounded event history" states a verb and resource, so an agent knows this retrieves event records. But "events" is undefined (input events? timer events? agent events?) and nothing distinguishes it from siblings like human_observe, human_status, or human_event_ack, which plausibly also expose event-ish data.
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?
"Discovery is delayed; agent push is unsupported" implies a polling model, which is a useful hint, but it is timing trivia rather than when-to-use guidance. There is no statement of when this tool should be chosen over human_event_ack (the natural acknowledgement counterpart) or human_observe.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.