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

Annotations only cover read-only/idempotent safety, so the description carries the real burden and does: stable uid surviving reschedules, phase='elapsed' explicitly NOT meaning published, schedule_status and schedule_basis='inferred' caveats for cadence-derived dates, coverage attached only to elapsed scheduled occurrences and null for cancelled/postponed, and days_back anchored to UTC midnight. That is behavioral context an agent cannot get from the structured fields.

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?

Front-loads the most decision-relevant content (US MACRO only, sibling routing) before the mechanics, and every clause is substantive rather than filler. It runs long and dense with parenthetical caveats, which hurts skimmability slightly, but nothing is truly redundant.

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?

An output schema exists, so return values need not be explained, yet the description still discloses the field-level semantics an agent must interpret (phase, schedule_status, schedule_basis, coverage, stable uid). For a read-only calendar tool with full schema coverage and annotations, nothing needed to call or interpret it correctly 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% and already documents days_back's UTC-midnight anchor, the 0/7 defaults, and the importance/event_keys filters. The description's note that the default 0 'still includes today's already-released prints with their coverage' restates the schema almost verbatim, so it adds only marginal meaning — baseline 3 is appropriate when the schema does the work.

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+scope up front: 'US MACRO only ... the official US economic calendar' with the enumerated release types (FOMC, CPI, PPI, NFP, GDP, PCE, retail sales, claims, JOLTS). It explicitly walls itself off from three siblings (alphai_earnings_calendar, alphai_tickers/next_report_date, alphai_earnings), so an agent can separate it from neighbors without opening any schema.

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?

Gives an explicit routing rule for the confusable siblings ('for who reports when use alphai_earnings_calendar', 'for one company's next date read next_report_date'), and names the when-to-use vs. when-not pairing with alphai_macro: this tool for forward-looking releases, alphai_macro once a release is out and you need its meaning. It even provides a natural-language query pattern to recognize ('what macro releases are coming this week').

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