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

With zero annotations, the description carries the full burden and delivers: events are RECONSTRUCTIONS from today's stored series, not live observations and not forecasts; occurred_at carries look-ahead; confirmation requires min_dwell days; drawdown uses the ATH up to that day and never a later one; the window is size-capped but position-free; silent rules are included. This is exemplary disclosure of behavioral traits that prevent misuse.

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?

Dense but every sentence earns its place — signal list, event fields, dual-date semantics, window mechanics, reconstruction caveat, filter, tier note — and the opening question front-loads the purpose. It is a long single paragraph, but the length is justified by the tool's nuance; a bit more structural segmentation would improve scannability.

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?

Despite having no output schema and no annotations, the description covers event contents (from/to state, dates, threshold params, btc_close, drawdown), the signal set, window behavior, and the critical reconstruction/look-ahead caveats. The only gap is the response envelope structure, but the essential semantics for correct invocation and interpretation are present.

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 coverage is 100%, so baseline is 3, but the description adds real value: it enumerates the 13 valid signal keys and explains end_date's window-positioning semantics ('capped in SIZE but free in POSITION') beyond the schema's generic 'last day of the window'. The occurred_at vs event_date distinction further clarifies output semantics relative to the requested window.

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+resource: an 'event log of discrete transitions across 13 declared signals', with all signal keys enumerated. The transitions/event-log framing clearly separates it from siblings like arena_get_signal_status (current state) and arena_get_signal_context, even without naming them.

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?

Provides substantive guidance: use event_date for any forward evaluation because occurred_at carries look-ahead, filter with `signal`, and the schema example shows how end_date positions the window at the October 2025 top. Lacks explicit when-not-to-use or named alternatives, but the context is clear enough to route correctly.

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