UK Data: US economic release calendar

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

Beyond the readOnly/idempotent annotations, it discloses genuinely useful behavior: unscheduled dates are omitted, the file does not indicate which period each date covers, output carries Eastern, UTC and local times, and the call costs 1 credit. These are exactly the caveats an agent needs before trusting the result.

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?

Three sentences, front-loaded with purpose, then limitations, then cost. The short-name list is duplicated in the schema, and the audience sentence is slightly soft, but nothing is padded.

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 carries the return-value burden and does state that one scheduled date per entry comes back with three time zones, plus the omission caveat. Ordering of results and any pagination or format detail are not specified, which is a minor gap for a calendar-listing 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: it enumerates the accepted short names and confirms a full BEA release name also works, and clarifies that the local time fields are driven by the time-zone argument. The year default and 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 first sentence names a specific verb and resource (return all dates in a year for one BEA release) and gives a concrete example that separates it from the sibling single-date tools like next_gdp_release. An agent can tell exactly what it gets without opening the 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?

It names the audience ("planners and analysts building a year's calendar"), which implies when to use it, but never routes to alternatives such as next_gdp_release or next_pce_inflation_release for a single upcoming date. Usage is implied rather than stated, and there is no when-not-to-use guidance.

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, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that: the specific return fields (quarter, bundled GDP estimate, times in Eastern/UTC/local), the default London timezone, and a 1-credit cost. It stops short of describing caching or failure behavior, but this is a low-risk read tool.

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 as a direct question, followed by tightly packed sentences that each add something: return contents, audience, exclusions, cost. No filler and no restatement of the tool name.

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 carries the burden of describing the return payload, and it does so precisely (release date, quarter covered, bundled GDP estimate, three timezone renderings). For a one-parameter read-only calendar lookup, nothing an agent needs 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?

The single timezone parameter is fully documented in the schema at 100% coverage, including the default Europe/London and IANA format examples. The description echoes 'your time zone (London by default)' but adds no new format or edge-case guidance, so the 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?

States a specific verb and resource: 'Returns the next scheduled release from the US Bureau of Economic Analysis calendar that includes national corporate profits.' It also disambiguates scope by naming the bundled GDP estimate and explicitly excluding profit figures and company earnings dates, so an agent can separate it from next_gdp_release or bea_release_dates_for_year.

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?

Names the intended audience ('equity strategists and economists tracking aggregate US profits') and the when-not condition ('gives the schedule only, not the profit figures or company earnings dates'). It does not explicitly route to a sibling tool, but the scope exclusion is enough to prevent most misselection.

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, non-destructive and openWorld, so the safety profile is covered. The description adds real value with source attribution (BLS schedule page) and a cost of 1 credit, but says nothing about data freshness or how often the schedule is refreshed.

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 question it answers, followed by return contents, source, and exclusions in a tight sequence. The time-zone default parenthetical partially duplicates the schema, a minor redundancy.

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?

No output schema exists, and the description compensates by enumerating returned fields (three time zones, reference month, up to 12 following dates). Cost and source are disclosed; only freshness/update cadence is absent for a schedule-driven 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 coverage is 100% with the single optional timezone parameter fully documented, so baseline is 3. The description restates the London default and clarifies that local time fields derive from it, but adds no format or IANA-validation detail beyond 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?

States a specific resource and question answered ('next US CPI inflation release'), plus exactly what is returned (release date/time, reference month, following scheduled dates up to 12). It explicitly distinguishes itself from the sibling next_pce_inflation_release and from inflation-figure tools.

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 scope conditions: dates only, no inflation figures, and explicitly not the PCE price index. It names the excluded sibling domain but does not explicitly route the agent to the alternative tool by name, so it falls short of a 5.

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 read-only, idempotent, open-world, and non-destructive behavior. The description adds substantial context beyond them: the returned fields (US Eastern, UTC, local time), default London timezone, BLS source, limitation to dates, and 1-credit cost. It does not contradict any annotation.

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 core question and then efficiently lists return fields, source, limitation, and cost. Every sentence contributes useful selection or invocation context.

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 low-complexity, single-parameter tool with no output schema, the description covers purpose, return values, source, timezone behavior, limitation, and cost. Nothing material for correct invocation 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?

The single optional timezone parameter is fully documented in the schema, including IANA format and default Europe/London. The description reinforces that the parameter controls local-time output and that US Eastern and UTC are also returned, but adds little syntax or semantic detail beyond 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 names the specific resource (Employment Cost Index) and the exact question it answers, defines ECI as quarterly US wage and benefit costs, and states it returns release dates rather than index values. This is enough to separate it from sibling release-date tools such as next_cpi_release without needing an explicit sibling comparison.

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 makes the intended use clear: retrieve the next ECI release date and following scheduled dates. It also sets a boundary by saying it gives dates only, not index values, though it does not explicitly name an alternative tool for CPI/GDP/etc. release dates.

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 the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower, yet the description still adds real value: the credit cost, the default local time zone, the fact that three releases are returned, and the explicit limitation that no figures or forecasts are included. It does not discuss freshness/caching of the schedule or what happens if a date is tentative, which keeps it from a 5.

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 key information (what it returns, in what detail, and the limits) is front-loaded in the first two sentences, with audience and cost trailing. The audience sentence ('For traders, economists...') is somewhat expendable padding, but overall there is little waste.

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 carries the burden of describing return content and does so concretely: estimate stage, quarter, triple time-zone times, and the following two releases. Combined with the explicit scope limit and cost, an agent has enough to call it correctly; only the handling of tentative/unconfirmed dates is unaddressed.

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 the single timezone parameter is fully documented in the schema, so the baseline is 3. The description only echoes that local times are returned 'in your time zone (London by default)', confirming the parameter's effect on the response rather than adding syntax or constraints beyond 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 opens with an explicit verb+resource question ('When is the next US GDP release?') and then states exactly what is returned: the next scheduled BEA release, its estimate stage (advance/second/third), the quarter, times in Eastern/UTC/local, plus the two following releases. This is clearly distinguishable from siblings such as bea_release_dates_for_year (a yearly calendar) and next_cpi_release (a different indicator).

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 names the audience and the planning use case ('For traders, economists and anyone planning around the GDP print') and states a clear exclusion: 'It gives the schedule only, not the GDP figures or forecasts.' What is missing is an explicit pointer to the alternative tool (bea_release_dates_for_year) when a full calendar is wanted, so the routing is implied rather than spelled out.

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 the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds genuinely useful context beyond them: the authoritative source (BLS schedule page), the fact it returns dates only and not payroll figures, the cap of 12 following dates, and a 1-credit cost. It does not describe caching/freshness of the schedule, which would be the remaining valuable 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 question-first framing front-loads the purpose, then packs return shape, source, exclusions, and cost into a few dense clauses with no filler. The parenthetical cost note and the trailing disclaimer are compact, though the description is slightly cluttered by stacking multiple asides in one paragraph.

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 compensates by enumerating the returned fields (release date/time in three zones, reference month, up to 12 upcoming dates) and the data source. For a zero-required-parameter lookup tool, nothing an agent needs to call 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 coverage is 100% and the single timezone parameter is fully documented with IANA examples and the Europe/London default, so the schema carries the load. The description adds marginal meaning by clarifying that the timezone controls the 'local time fields' and that results also include US Eastern and UTC regardless, but that is close to restating 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 leads with a specific question naming the exact resource (US Employment Situation: nonfarm payrolls and unemployment rate) and states the concrete return (next release date/time plus up to 12 following dates). It is clearly distinguishable from siblings such as next_jolts_release, next_cpi_release, and bea_release_dates_for_year because it names the underlying BLS report and explicitly excludes ADP payrolls and weekly jobless claims.

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 strong when-to-use context plus explicit exclusions (ADP private payrolls, Department of Labor weekly claims), which steers an agent away from misusing it. It stops short of naming the alternative tool an agent should call instead for ADP or claims data, so it is not a full when/when-not/alternative triad.

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?

Beyond the annotations (readOnly, idempotent, openWorld), the description adds real behavioral context: default timezone handling, the 10:00 ET release convention, the caveat that the BLS page sometimes lists only one or two upcoming dates, and the cost of 1 credit. It doesn't disclose failure behavior when no date is listed, which keeps it below a 5.

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?

Content is front-loaded with the core question and answer shape, then caveats. It is slightly dense with asides (timing comparison, source limitation, credit cost), but each sentence contributes useful information 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?

With no output schema, the description does the work of explaining the return payload (three time zones plus reference month) and source reliability, which is what an agent needs. The only missing piece is what happens when BLS lists no future date at all.

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 the single optional timezone parameter is already well documented with IANA examples. The description restates the London default, adding mild confirmation but no new syntax or format detail, so the schema carries the load and 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 opens with a specific question naming the exact resource (next JOLTS release) and states precisely what comes back: next release date/time in three zones plus reference month. It explicitly contrasts itself with the sibling tool next_jobs_report_release by noting JOLTS is 10:00 ET rather than 08:30 ET, so an agent can discriminate without opening either 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?

It gives clear context for use (scheduling/checking the next release) and an explicit when-not signal: 'Gives dates only, not the job openings figures,' which steers agents away if they want the actual data. The only gap is that it doesn't name the tool to use for the underlying figures.

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?

Beyond the readOnly/idempotent annotations, the description discloses the credit cost, the default time zone (London), and that times are returned in Eastern, UTC and local. It does not mention caching or how far ahead the schedule extends, but the added operational context is solid for a read-only lookup.

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 lead question front-loads the task and the detail follows in a logical order. The audience sentence ('For traders, economists and Fed watchers') and the cost note are filler-adjacent, but overall the text is tight for the amount of context delivered.

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 one-optional-parameter, read-only schedule lookup with no output schema, the description covers what is returned (the covered month and times in three zones), the time-zone behavior, the cost, and the scope limit. An agent has everything needed to call it and interpret the result.

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 the single optional parameter is fully documented in the schema (IANA zone, default Europe/London). The description's '(London by default)' merely restates the schema, so 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?

States a specific verb and resource ('next scheduled Personal Income and Outlays release') and explicitly says which inflation measure it carries (PCE and core PCE), which is enough to separate it from the CPI, PPI and jobs-release siblings 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?

Gives a clear scope boundary — 'It gives the schedule only, not the inflation figures' — which tells an agent when not to use it. It never names an alternative (e.g. next_cpi_release or bea_release_dates_for_year) for related needs, so it falls short of full when-to-use/when-not 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/idempotent/non-destructive, so the burden is light. The description still adds real value beyond them: the data source (BLS PPI schedule page), the shape of the return (next date plus up to 12 following dates), the time zones returned, and a credit cost. It stops short of saying what happens when the schedule page is unreachable or how stale the cached data may be.

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 as a plain question the tool answers, followed by return shape, data source, scope exclusion, and cost in that priority order. Every sentence carries distinct information; nothing is repeated from the name or schema.

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, so the description must describe return values, and it does: next release date/time in three zones, reference month, and up to 12 following dates. For a single optional-parameter, read-only lookup, nothing an agent needs in order to call 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 coverage is 100% and the timezone parameter is already documented there, so the baseline would be 3. The description adds meaning beyond the schema by explaining that the parameter drives a third 'your time zone' field alongside always-present US Eastern and UTC fields, clarifying the parameter's effect on output rather than just its format.

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 a specific resource (US PPI release schedule) and a specific question it answers, and distinguishes itself from the many other release-date siblings (next_cpi_release, next_gdp_release, next_jolts_release) by naming the exact index. An agent can route to it without opening the 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?

Explicitly bounds scope with 'Gives dates only, not the index values', which tells the agent when this tool is insufficient, and flags the 1-credit cost so the agent can weigh alternatives. It does not name a sibling to use for actual index values, so the routing is implied rather than explicit.

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