get_events

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does explain that events from four sources are unified on one clock and why that matters (reconstructability). However, it doesn't disclose ordering behavior, pagination, whether it's bounded, or how limit/truncation works beyond what the schema already says. The clock-unification rationale adds genuine context beyond the schema.

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 tight sentences. The first states the purpose directly, and the second explains the unifying-clock rationale and why that matters. Zero filler, front-loaded with the verb+resource declaration, and the closing rationale is genuinely useful rather than padding.

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?

The description captures the essential domain context (unified clock, four event sources, reconstructability rationale) which is the key complexity this tool addresses. The full schema coverage plus an existing output schema means return-value explanation is not required. It could mention ordering (schema says 'most recent first' via limit) but that's already in the schema, so the description is adequately complete.

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% and all five parameters are documented in the schema (filters for label, origin, limit, last_seconds). The description adds conceptual context about what event types exist (board markers, annotations, stim commands, manual notes), which enriches the 'origin' filter meaning. But it adds little semantically beyond the schema's own parameter descriptions; baseline 3 with modest credit for the origin taxonomy.

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 this reads 'the session's event log' and explains what sorts of events land there, distinguishing it from sibling tools like list_recording_events, get_epoch_around_event, and log_event. The verb+resource is clear, but it doesn't explicitly contrast with siblings by name, and get_epoch_around_event / list_recording_events could be confused without further contrast.

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 implicitly conveys 'use this to inspect the full unified event log' and explains events are unified on a single clock for reconstructability, which suggests when it's useful. However, it doesn't explicitly state when NOT to use it (e.g., when to use list_recording_events or get_epoch_around_event instead), so alternatives aren't clearly delineated.

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