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

Beyond the readOnlyHint it discloses high-value behavior: days above 180 is REFUSED, results cached 6h, and critically that every failure returns events=[] so the agent must inspect source_status rather than trust an empty array. It also notes the free Oxford Ledge API key requirement configured by the operator.

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-loaded with the core definition and exclusion before the field/return details; every clause (failure mode, cache, auth, source) carries operational value. It is dense and uses heavy capitalization/abbreviation, which trades a little readability for density.

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 no output schema, the description fully specifies the return shape ({days, events, count, withheld, source_status, error} and per-event fields), explains label_source semantics, and covers the silent-failure trap and auth prerequisite. Nothing an agent needs to call or interpret it 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 coverage is 100% and already documents days (default 90, min 1, max 180), so baseline is 3. The description adds meaning beyond the schema by stating the over-180 case is actively REFUSED rather than merely bounded, which changes how an agent should handle a large value.

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 precise verb and resource — 'Upcoming US macro DATA-RELEASE DATES (a schedule, not estimates)' — and enumerates the 8 tracked releases, so the agent knows exactly what comes back. It also excludes adjacent concepts ('no values; no FOMC dates'), separating it from get_fred_data and from earnings-calendar siblings.

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?

Clear context for when to call it (forward-looking release schedule) and implied alternatives via 'no values' (use get_fred_data for values) and 'no FOMC dates'. It does not name an explicit sibling alternative or state exclusions like 'use ol_earnings_calendar for company events', so a 4 rather than 5.

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