CEV-OS Data API

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds two genuinely useful operational facts not in annotations: the service is free and requires attribution to listed sources. However it says nothing about result volume, ordering, or how 'impact tier' is assigned.

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?

The trigger condition is front-loaded well, but roughly half the text is licensing/attribution boilerplate (source list, BEA disclaimer) that is administrative rather than selection-relevant. The useful capability information is compressed into one long clause while the legal text gets equal space.

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?

There is no output schema, and the description does convey what a result contains (events of five kinds, each with an impact tier), which is the key missing piece. Remaining gaps – no pagination/limit note, no ordering, no explicit sibling routing – are modest for a zero-required-parameter calendar lookup.

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%, with hours range, kinds enum values, min_tier enum and include_estimated default all documented in the schema. The description only echoes the 'next hours' window and 'impact tier' concept, adding no syntax or defaulting detail beyond the schema – baseline 3.

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: returns market-moving events (US macro, FOMC, Treasury auctions, earnings, options expiry) over a look-ahead window, each tagged with an impact tier. The event-type enumeration makes the scope concrete, but it never names the obvious sibling (get_macro_calendar) that overlaps with its 'macro' and 'fed' kinds.

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?

'Use this when you need to know whether the next hours contain a market-moving event' gives a clear trigger condition, but there are no exclusions and no alternatives are mentioned despite several calendar/regime siblings. An agent must infer on its own why it would pick this over get_macro_calendar.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety is covered. The description adds genuinely useful non-schema context, namely the attribution obligation ('Data provided for free by IEX') and data provenance (release times from SEC EDGAR, statistics from PrintLine). It says nothing about behavior when a ticker has too few earnings events, or about the required-ticker mismatch implied by 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?

The use case and data description are front-loaded and tight, but the license paragraph is bloated: 'IEX Historical Data Terms of Use' is restated three times plus a URL, which is boilerplate repetition rather than agent-relevant content.

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?

For a single-parameter read-only tool with no output schema, the description conveys what is returned (day-1/day-5 move distributions) and the legal/provenance obligations. It could go further on sample size, metric shape (mean vs median vs range), and minimum history requirements, but nothing essential to calling 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?

Only one parameter and schema description coverage is 100% (the schema itself documents the S&P 100 / NASDAQ-100 ticker restriction), so the baseline is 3. The description adds no extra ticker semantics such as case handling, symbol format, or what happens for out-of-index tickers.

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 a precise resource: day-1/day-5 move distribution per ticker around SEC 8-K Item 2.02 earnings releases, which is unmistakably different from the macro/catalyst/status siblings. It stops short of explicitly naming or contrasting any sibling (e.g., get_catalysts, which also touches earnings dates), so routing is inferential rather than stated.

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?

'Use this when sizing an earnings trade' gives a concrete scenario for invocation, which is more than most definitions offer. There are no exclusions, prerequisites, or named alternatives, so an agent must infer that this is not a general price-history tool.

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

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

Annotations already declare readOnly, idempotent and open-world, so the safety profile is covered. The description adds genuinely non-structured context: the tool is free, carries a cleared_with_attribution license, requires attribution to GDELT/UCDP/USGS/GDACS, and explicitly warns it is 'not for life-safety use' — a material usage caveat an agent would not otherwise know.

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?

The usage trigger is front-loaded, which is good, but the bulk of the text is a dense run-on of license names, attribution URLs and caveats stuffed into one sentence. The licensing information earns some place, yet it is compressed with the functional sentence rather than separated, hurting 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?

For a read-only, zero-required-parameter filter tool with full schema coverage the calling mechanics are complete. However, there is no output schema and the description says nothing about the shape of returned incidents (fields, severity scale meaning, asset tag ordering, pagination or result caps), which is a real gap for an open-world data tool.

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 each of the four parameters (asset, region, since_hours, min_severity) including its enum, bounds and default is documented in the schema. The description only restates the asset vocabulary loosely, adding no format, matching or interaction guidance beyond the schema — 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?

The description states the resource concretely: recent geopolitical, conflict and natural-hazard incidents mapped to asset classes and liquid proxies, with examples of the proxies (oil, grains, gas, semis, gold, Treasuries, country ETFs). It never names a verb like 'list/return' and does not distinguish itself from siblings such as get_catalysts or get_macro_calendar, so a 4 rather than a 5.

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?

'Use this when you need recent geopolitical, conflict and natural-hazard incidents mapped to assets' gives a trigger condition, so usage is implied rather than absent. It offers no exclusions, no prerequisites, and no pointer to an alternative sibling tool for overlapping queries (catalysts, macro calendar), leaving routing to inference.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful operating constraints — free, license cleared, mandatory attribution with named source agencies — but says nothing about result ordering, whether unreleased events appear, or how missing actual/prior values are represented. The large licensing block is required boilerplate rather than behavioral 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?

The usage trigger is front-loaded correctly, but roughly half the text is attribution/licensing boilerplate that, while legally required, crowds out operational detail. Every sentence is defensible, yet the useful signal-to-total ratio is mediocre.

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 five optional parameters at full schema coverage and no output schema, the description covers purpose, coverage universe, and attribution obligations adequately. Return shape is described only loosely ('actual and prior values'), which matters less here because there is no output schema to lean on, but an agent still lacks ordering and pagination expectations.

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 the baseline is 3, but the description earns a bump by mapping plain-language event names ('payrolls', 'claims', 'ISM dates') onto the schema's coded enum values such as employment_situation and jobless_claims. Date defaults and the limit range are left entirely to the schema.

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 a specific verb/resource pair ('official US release times') and enumerates the covered event families (CPI, PPI, payrolls, GDP, PCE, FOMC, ISM), so an agent knows exactly what content comes back. It doesn't explicitly contrast itself with siblings like get_release_status or get_macro_regime, leaving some ambiguity about which one to pick.

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?

'Use this when you need official US release times ... with actual and prior values once released' gives a clear usage context, including the distinction between scheduled dates and released values. There are no explicit exclusions or named alternatives, so the routing decision against siblings is still partly inferred.

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

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

Annotations already cover read-only, idempotent and open-world behavior, so the description is free to add the non-obvious operational facts: that the call is free, the license state is cleared_with_attribution, and attribution to five named sources is required. It does not state update cadence, freshness lag or failure behavior, which is the remaining gap for a 'slow-moving' indicator.

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?

Purpose, usage trigger and inputs are front-loaded in the first sentence; cost and license follow. The attribution block is bulky (five agencies plus series IDs) but is compliance-relevant content rather than filler, so it earns its space even though it doubles the length.

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 and no parameters, the description carries the burden of describing the return value, and it does name the flag's three possible states plus the five underlying inputs. It stops short of describing the response structure or how the regime is computed from those inputs, so an agent cannot predict field names or thresholds.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool applies. The description correctly does not invent options or filters.

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 a specific resource (a single slow-moving macro regime flag with risk_on / neutral / risk_off values) and enumerates the inputs behind it, so the agent knows exactly what it gets back. It implies differentiation from get_market_mood via 'slow-moving' but never names a sibling, so the boundary is inferential rather than explicit.

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?

'Use this when you want one slow-moving macro regime flag' gives a clear selection criterion, and 'slow-moving' implicitly contrasts with faster-moving siblings like get_market_mood or get_catalysts. There is no explicit when-not or named alternative, so an agent must infer the routing.

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

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

Annotations already declare readOnly, openWorld and idempotent, so the safety profile is covered. The description adds genuinely non-obvious context: both series are free, each carries its own timestamp and source (signalling possible staleness/skew between the two), and citation/attribution is legally required.

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?

The usage cue is front-loaded and the data sources follow immediately. The trailing licensing/attribution text is verbose but is compliance boilerplate an agent may need verbatim, so it earns most of its space.

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 input params and no output schema, the description does the work of explaining what comes back: two series, each with timestamp and source. It omits scale/units (e.g., the 0-100 Fear & Greed range) and whether a history window is returned, which are minor remaining gaps.

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?

The tool takes zero parameters, so there is nothing to disambiguate and the schema is empty by design; baseline 4 applies. The description implies the returned data is fully self-contained with per-source timestamps.

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?

Names the concrete resources precisely: Crypto Fear & Greed from alternative.me and the VIX daily close from FRED. The framing as a 'quick risk-sentiment read' implicitly separates it from the macro-regime and macro-calendar siblings, though it never names an alternative 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?

'Use this when you need a quick risk-sentiment read before acting' gives a clear triggering context tied to a decision point. It stops short of stating exclusions or pointing to get_macro_regime/get_macro_calendar as the alternative for deeper macro context.

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

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so safety behavior is covered. The description adds useful context beyond annotations: it says the service is free, license-cleared, attribution-required, names the source systems, and notes that detection timestamps are measured by cev-os. It still does not describe rate limits or response structure in detail.

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?

The description is front-loaded with the usage trigger and return information, then moves into licensing/provenance details. It is somewhat dense and includes legal boilerplate, but the attribution block is relevant to use and nothing is seriously 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?

For a read-only status lookup with full schema coverage and no output schema, the description covers the key return concepts: whether a release is out, when it was first seen, and actual/prior/revision values. It also covers provenance and licensing. Minor gaps remain around explicit sibling differentiation and output formatting, but the essential invocation context is 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 description coverage is 100%, so the schema already documents all four parameters, including date patterns, event types, and ticker behavior. The description reinforces the event categories and earnings use case, but does not add syntax, defaults, or constraints beyond what the schema provides.

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 a specific verb/resource: checking whether a scheduled US release or an S&P 100/NASDAQ-100 earnings 8-K is out, plus first-seen timing and actual/prior/revision values. It is clear enough to distinguish the core function, but it does not explicitly contrast itself with siblings such as get_macro_calendar or get_earnings_reactions.

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?

It gives an explicit trigger: 'Use this when you need to know whether...' and lists the covered release categories and earnings type. It does not specify when not to use it or name alternative tools for calendar-style or reaction-style queries.

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