UK Data: US politics and government

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

Annotations already cover the read-only/idempotent safety profile, and the description still adds substantive behavior: the 1994-onward coverage boundary and the explicit warning that older orders are not found, plus the upstream source and a credit cost. The coverage limitation is exactly the kind of failure mode an agent needs before calling.

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 verb, resource, and return payload, then the use case, then the caveat and cost. Mostly efficient, though 'without guessing' is filler and the parenthetical cost tag could be tighter.

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, but the description compensates by enumerating the returned fields. With coverage limits, source, and cost all disclosed, an agent has everything needed to call this correctly and interpret a not-found 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 coverage is 100% and the single parameter is already documented, so the schema does the heavy lifting. The description nonetheless anchors the expected input value with a concrete example (14148), which mildly reinforces format expectations beyond the structured field.

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 ('Looks up one US executive order by its EO number') and then enumerates exactly what comes back: title, signing and publication dates, Federal Register citation, president, and PDF. An agent can distinguish this from sibling tools like federal_register_document without opening a 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 a concrete usage scenario ('sees an EO number in the news or a court filing'), which implicitly answers when to reach for this tool. It does not name an alternative or exclusion path, so it stops short of full when/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 and open-world, so the safety profile is covered. The description adds value beyond that: the upstream source (FederalRegister.gov API), the 1-credit cost, the shape of the returned record, and the important limitation that full text is excluded and must be fetched via html_url or pdf_url. It does not discuss failure modes for an unknown document number, which keeps it short of 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?

Front-loaded with the verb and key, then audience, source, constraints and cost in a logical order; no filler sentences. Minor waste from restating the '90 FR 8443' exclusion that the schema already carries, but overall tight for the amount of information conveyed.

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 compensates by listing the fields returned (type, agencies, publication/signing dates, FR citation, effective date, comment deadline, docket, official PDF). Combined with the cost note and the full-text redirect, an agent has everything needed to call this correctly and to know what to do with 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?

With a single parameter at 100% schema coverage, the schema already defines document_number and even includes the 'not an FR page citation such as 90 FR 8443' caveat. The description repeats that same distinction rather than adding new meaning such as format normalization or behavior on ambiguous numbers, so the baseline of 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 ('Fetches one Federal Register document by its document number') and immediately enumerates what the record contains (type, agencies, dates, FR citation, docket, govinfo PDF). It also distinguishes itself from adjacent concepts by naming what it is not: not a citation resolver and not a full-text source. No sibling tool covers this exact primary-record lookup, so the scope is unambiguous.

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 audience and precondition ('who have the document number from a notice, docket or URL and want the primary record rather than a secondary summary'), which tells the agent both when to pick this and when a summary tool is preferable. It also states two negative conditions — it will not resolve '90 FR 8443' and will not return full text — and redirects to html_url/pdf_url for the latter.

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, which already declare this a read-only, idempotent, non-destructive open-world lookup, the description adds useful behavior: newest-first ordering, DC-area scope, the types of postings included, each posting's applied/posted/replaced dates, and gaps in coverage for ordinary open days and older years. It also discloses the one-credit cost, though it does not describe response shape or pagination behavior 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 a concrete question and an explicit listing statement, then moves through examples, use cases, caveats, and cost. It is somewhat long for a simple two-parameter tool, but every sentence contributes to scope, usage, or limitations.

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, two-optional-parameter tool with rich annotations and full schema descriptions, the definition covers what is listed, ordering, coverage limits, use cases, and cost. No output schema exists, but the description sufficiently characterizes the returned postings and their dates.

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 input schema fully documents both optional parameters, including types, ranges, defaults, and the paging purpose of startrow. The description adds no parameter-specific meaning beyond the schema, so the baseline score of 3 is appropriate for 100% schema description coverage.

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 a specific resource and scope: OPM's past operating-status postings for the Washington, DC area, with examples of closure types and newest-first ordering. The word 'past' and the opening question distinguish it from current-status siblings such as us_government_operating_status or us_shutdown_now.

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 use cases (HR, payroll and contractor questions) and important caveats: ordinary open days are mostly not listed and online history covers recent years only. It does not explicitly name an alternative tool for current status, but the history-versus-current framing makes the intended usage clear.

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 safety is covered; the description adds genuinely new context: the geographic scope limit, the exclusion of agency-level closures, the content of the response (status, applicable date, OPM employee guidance), and a cost of 1 credit. That is useful operational detail beyond the structured fields, though it says nothing about caching or how often the status refreshes.

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 is front-loaded and the scope caveat follows logically, with the cost line clearly separated at the end. The parenthetical list of status values is long but earns its place by telling the agent what to expect. Minor redundancy between 'US Office of Personnel Management's current operating status' and the 'OPM's guidance' phrasing.

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 zero-parameter, no-output-schema lookup, the description covers what is returned, the geographic limitation, and the exclusions, which is most of what an agent needs to decide and call correctly. It could be complete at a 5 with an explicit pointer to the historical sibling or a note on how current the status is.

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 no parameter meaning for the description to establish; the baseline applies. The description correctly implies a no-argument call ('Are federal offices open today?') and adds no misleading input expectations.

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?

It opens with a concrete question the tool answers ('Are federal offices open today?') and names the exact source and resource (OPM's current operating status for the federal government in DC). The enumerated possible return values (open, delayed arrival, early departure, closed, unscheduled leave/telework, lapse in appropriations) make the tool's output unmistakable against any sibling.

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 states concrete use contexts (snow days, funding deadlines) and gives an explicit when-not: DC only, agencies elsewhere set local status, and it does not cover individual agency closures. It stops short of naming the obvious siblings (opm_status_history for past statuses, us_shutdown_now for shutdown specifics), so the alternative 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.

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

Beyond the annotations, which already establish read-only, idempotent, open-world, and non-destructive behavior, the description adds the data source, the output shape (yes/no, partial vs full lapse, exact OPM wording, posted timestamp), and important limitations about forecasting and agency staffing decisions. It also discloses the cost of one credit.

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 is generally efficient, with each sentence adding useful scope, output, or limitation detail. It is slightly longer than strictly necessary for a no-parameter tool, but there is little wasted wording.

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 simple read-only lookup with no parameters and no output schema, the description is complete: it explains what question is answered, what source is used, what the response includes, and what the tool does not cover. An agent has enough information to call it correctly.

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 has zero parameters, so there is no parameter semantics to explain and the baseline is 4. The description correctly adds no irrelevant parameter detail.

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 gives a specific verb and resource: it answers whether the US government is shut down right now using OPM's current operating status, and it explains that partial and full lapses are distinguished. It does not explicitly differentiate itself from the sibling tool us_government_operating_status, so it falls short of a 5 despite being otherwise precise.

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?

The description implies the use case through the direct question 'Is the US government shut down right now?' and gives one scope limitation: it does not forecast funding deadlines. However, it never names an alternative tool such as us_government_operating_status or opm_status_history, so routing guidance is left implicit.

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