Retrieve bounded native events using a monotonic cursor and stream epoch, preserving continuity across provider reconnects.
Read bounded native events with a registry-owned monotonic cursor, stream epoch, and retention-gap metadata across provider reconnects.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| nativeId | Yes | ||
| provider | Yes | ||
| timeoutMs | No | ||
| afterSequence | No |
Changes observed during successful MCP inspections.
v0.3.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark readOnlyHint=true, and the description goes beyond that by disclosing registry-owned monotonic cursors, stream epochs, retention-gap metadata, and reconnect behavior. This adds useful non-obvious behavioral context, though it does not cover error/rate-limit behavior.
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 a single dense sentence with no filler and front-loads the core 'read bounded native events' action. It could be clearer but is efficient.
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?
With five parameters, 0% schema coverage, no output schema, and no usage guidance, one sentence is not enough for an agent to invoke this correctly. Missing parameter meanings, page-size semantics, and response shape leave significant gaps.
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 carries the burden of explaining five parameters. It only hints at cursor semantics ('monotonic cursor') and bounded reads, while provider, nativeId, limit, and timeoutMs are left unexplained; it barely maps to the actual parameters.
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 states a specific action ('Read bounded native events') and adds distinguishing details about cursor, stream epoch, and retention metadata. It is clear about the resource, but it does not explicitly contrast with the sibling events_read, so an agent must infer the pagination/page distinction.
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 phrase 'across provider reconnects' implies a use case for stable, resumable event paging, but the description never states when to choose events_page over events_read or any other sibling. Usage context is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.