event_cursor

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

With no annotations, the description carries the behavioral burden well: it discloses the O(1)/no-scan cost profile, the anchor/monotonic semantics (only events after now), and the sentinel return (0 for empty). It never states read-only or auth/permission needs, but for a pure cursor read this is a solid disclosure.

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?

One dense sentence with the anchor semantics front-loaded and cost/return details in tight parentheses. Every clause earns its place (O(1), no scan, append-after-now scoping, empty sentinel).

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 an output schema present, the return shape need not be explained, and params are fully covered by the schema. The description supplies cost and usage framing, giving an agent enough to call it; only explicit sibling routing 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?

Schema description coverage is 100%, so stream, agent_id, and project_root are already fully documented in the schema (including scope and enum-ish stream values). The description adds no parameter-level meaning beyond what the schema provides, so the baseline 3 applies.

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 ("Return the stream's CURRENT END as a cursor") and adds the operational role ("pre-flight monitor anchor"). It implicitly separates this from event_get/event_wait by framing it as an anchor rather than a reader, but never names a sibling explicitly.

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?

"Pre-flight monitor anchor so you see only events appended after now" gives a clear when-to-use context: grab this before monitoring so subsequent reads are scoped to new events. No explicit when-not or named alternatives (e.g. event_get vs event_wait) are given, 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.