StatCite — Verified Economic Statistics

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

Even though annotations already declare read-only, idempotent, and non-destructive behavior, the description adds valuable context: it explains that differences are methodological (never an error), that the result specifies which definition each value carries, and that down sources report errors in place without sinking the comparison. These are meaningful behavioral details beyond the annotations.

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 four sentences long, front-loaded with the main action, and every sentence adds value: it covers purpose, usage, behavioral notes, and error handling. There is no fluff or repetition.

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?

Despite lacking an output schema, the description comprehensively explains what the tool returns (values side by side, citations, spread, definition labels) and how it handles source outages. It provides enough context for an agent to select and use the tool correctly, even in a complex multi-source comparison scenario.

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 parameters are already well documented. The description adds some context by clarifying the tool fetches 'one indicator for one country' and iterates over all sources, but it does not significantly enhance the parameter semantics beyond what the schema provides. Baseline 3 is appropriate.

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 uses a specific verb ('Fetch') and clearly defines the resource: one indicator for one country across EVERY official source, showing values side by side with citations and spread. This distinguishes it from siblings like get_indicator (which likely returns a single value) and verify_stat (which checks 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?

The description explicitly states when to use the tool: 'Use when sources disagree, when you need to know WHICH official number to cite, or to check how large the methodological gap is.' It gives clear context but does not name alternative tools or provide explicit when-not-to-use guidance, so it falls short of a perfect 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 readOnlyHint=true and destructiveHint=false. The description adds meaningful context by specifying data sources (World Bank, IMF DataMapper API, current vintage) and that 'each value carries its own citation.' This goes beyond the annotation baseline without contradicting it.

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?

Two sentences, no fluff. The first sentence front-loads the purpose and lists all indicators; the second states the value proposition and citation feature. Every word earns its place.

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 one parameter and no output schema, the description lists all returned indicators, their sources, and citation behavior, effectively describing the output. It also provides a use case, making it fully adequate for tool selection and invocation.

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 schema covers the single parameter at 100% with 'ISO3/ISO2 code or English name.' The description does not add syntax or format details; it only implies that the parameter selects a country for the snapshot. Baseline 3 is warranted due to complete schema 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 clearly states the tool provides 'a country's headline economic picture' in one call, enumerating 11 specific indicators. It differentiates from siblings like get_indicator and get_series by being a comprehensive snapshot rather than a single data point or series.

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 via 'Ideal for country briefs and report openers,' but does not explicitly state when to avoid this tool or name alternatives such as get_indicator. This is clear context without exclusions, so a 4 is appropriate.

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 label the tool as read-only, idempotent, and non-destructive. The description adds what is returned (observations and citation) but does not disclose edge cases like invalid IDs or data freshness. It adds some value beyond annotations.

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?

Two sentences, front-loaded with the action and format, no unnecessary words. Every sentence serves a purpose.

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 tool with one parameter and an output schema, the description adequately explains the input format and output contents. The term 'recent observations' is somewhat vague but acceptable given the output schema likely provides structure.

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 0% (no parameter description), but the description provides the expected format ('indicator/<key>/<ISO3>'), which adds critical meaning beyond the raw type 'string'.

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 clearly states the verb 'Fetch' and the specific resource 'full data for a result id returned by search', including the required ID format. This distinguishes it from sibling tools like search and get_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?

The description explicitly links usage to results from search, providing clear context. It does not explicitly list when not to use or alternative tools, but the context is sufficient for correct selection.

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, non-destructive behavior. The description adds valuable context beyond annotations: the method and citations are stated explicitly, currency coverage (~30 majors vs ~90 others), and the date-range behavior (since 1999). No contradiction with annotations.

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 two sentences, front-loaded with the main purpose, and every clause adds useful information. It avoids redundancy and is easy to scan.

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 tool with no output schema, the description reasonably explains the conversion sources, date formats, and currency coverage, plus notes that method and citations are included in the response. It could be slightly richer by stating the output shape, but it is adequate for the tool's complexity.

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 descriptions cover 75% of parameters (to, from, date), giving ISO codes and date format. The description goes further by explaining the meaning of the date format ('YYYY-MM-DD' for daily, 'YYYY' for annual average) and giving concrete currency examples (BBD, XCD, JMD, KES), which helps select correct parameter values.

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 clearly states the tool converts an amount between currencies using official reference rates, with specific sources (ECB daily, World Bank annual). This distinguishes it from sibling tools like inflation_adjust or get_series, and the verb 'Convert' plus resource 'currencies' is specific.

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 provides clear contextual guidance on when to use daily ECB rates versus World Bank annual rates, and exactly how to pass the date parameter. However, it does not explicitly mention alternatives or when not to use this tool relative to sibling tools.

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 and idempotentHint, but the description adds valuable behavioral context: it returns a full citation, mentions fallback behavior, and explains strict_source reproducibility mode. This goes beyond what annotations provide, though it doesn't cover every possible edge case.

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 three sentences, front-loaded with the core purpose, then lists supported indicators, citation details, and usage guidance. Every sentence provides value with no wasted words or redundant schema repetition.

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 appropriately discloses the return format (observations plus a full citation) and key behavioral aspects like fallback and strict_source. It covers the main usage context and parameter hints adequately, though a bit more detail on the response structure would make it complete.

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. The description adds clarifying meaning beyond the schema, such as 'Use ISO3 codes or plain country names' and 'Registry key' for the indicator, enriching the parameter semantics. However, it doesn't fully detail every parameter, relying on the schema for specifics.

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 clearly states the tool's purpose: 'Get official values for a common economic indicator' and lists many indicator types. It also differentiates from siblings by positioning it as 'Start here for most questions' and explicitly mentioning search_indicators for when the indicator key is uncertain.

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 says 'Start here for most questions' and directs users to 'use search_indicators if unsure of the indicator key.' This provides clear when-to-use and when-not-to-use guidance with a named alternative.

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 readOnlyHint, openWorldHint, idempotentHint, the description reveals that FRED is permanently disabled and will return an explanatory disabled response, that dbnomics supports dated editions for reproducibility, and that every response includes a full citation. These are valuable behavioral details not present in annotations.

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 information-dense but well-structured: main action first, followed by id format breakdown, disabled source exception, capabilities, and alternative. Each sentence adds unique information, earning its place.

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?

Despite no output schema, the description covers the tool's scope, exceptions, capabilities, and alternatives. It mentions citation in responses, providing some output context. For a complex tool with multiple id formats, it is quite complete.

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 description substantially expands on series_id, detailing all supported id formats with examples and requirements. It also mentions year filters and transforms (yoy, pct_change, index), covering start_year, end_year, and transform parameters. This compensates for the limited schema descriptions on those params.

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 explicitly states it fetches any supported series by explicit id, enumerates the id formats, and distinguishes from get_indicator by advising preference for common indicators. It clearly specifies the resource (series) and the action (fetch).

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 explicitly says to prefer get_indicator for common indicators, and notes that FRED ids are permanently disabled, making them unretrievable. It also gives contextual requirements like 'needs country' for worldbank and imf ids, guiding appropriate usage.

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?

Adds meaningful behavioral details beyond the annotations: returns adjusted amount, exact index values, formula, citation, and specifies annual-average precision. This enriches the agent's understanding of expected output and processing, with no contradiction to annotations.

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?

Two sentences that are dense with useful information, front-loaded with the primary verb and example. No fluff or redundancy; every phrase adds value.

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?

Despite lacking an output schema, the description clearly states what will be returned and precision. It doesn't cover edge cases like invalid years or missing CPI data, but for a straightforward conversion tool, the level of detail is adequate.

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 low (25% only for country). The description gives an illustrative example but doesn't elaborate on the meaning/format of amount, from_year, or to_year beyond the context. It partially compensates but leaves gaps for required numeric parameters.

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 clearly states the tool's function: converting a nominal amount between years using official CPI, with a concrete example. It distinguishes itself from siblings like fx_convert (currency conversion) by explicitly focusing on inflation adjustment across years.

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?

Provides clear context via the example and notes that it works for any country with CPI data (default USA). However, it doesn't explicitly mention when to prefer this over alternatives like fx_convert, relying on implicit distinction.

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 destructiveHint=false, so the agent knows this is a safe read operation. The description adds valuable behavioral context beyond annotations by detailing which specific sources are included (World Bank, IMF, DBnomics fallback, ECB, FRED disabled) and that it provides attribution lines, giving the agent concrete expectations about output content.

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 a single sentence but packs substantial information without fluff. It front-loads the core purpose ('The official sources behind StatCite') and then details the sources and what each offers. The sentence is slightly dense with parentheticals, but every clause earns its place; it is concise yet comprehensive.

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?

Given the tool's simple nature (no parameters, no output schema), the description is fully complete. It states exactly what will be returned: the list of sources, what each covers, its license, and the attribution line. There is no ambiguity about the tool's function or expected output, and the low complexity means no additional details are needed.

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 zero parameters, the schema provides no semantics to explain. The description doesn't need to add parameter meaning because there are none. Per the rubric, a baseline of 4 is appropriate for tools with no parameters, and the description gives sufficient context about what the list will contain.

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 clearly states the tool's purpose: listing official sources, their coverage, licenses, and attribution lines. It uses specific action verbs ('List') and resource types ('data sources, licenses, and attribution rules'), and distinguishes itself from sibling tools like compare_sources by focusing on enumeration rather than 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?

The description makes the usage context clear: it is the go-to reference for understanding what sources exist behind StatCite, what they cover, and how to cite them. While it doesn't explicitly exclude alternatives or name sibling tools, the guidance is implied strongly enough that an agent would know when to call it (e.g., before citing or when source availability is in question).

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 provide readOnlyHint, openWorldHint, and idempotentHint. The description adds value by specifying that the tool returns 'result ids that can be passed to fetch,' giving insight into the output format. No contradictions with annotations.

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 concise—two sentences—with no filler words. It front-loads the purpose and examples, then adds usage guidance efficiently.

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?

Given the single parameter and presence of an output schema, the description is complete: it explains the input, output (IDs), and tool context. No further information is necessary for correct use.

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 0% schema description coverage, the description fully compensates by explaining the 'query' parameter as free text with examples ('inflation barbados', 'government debt japan'). This adds meaning far beyond the bare schema specification.

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 clearly states the verb ('Search'), the resource ('official economic statistics'), and the method ('by free text'). It provides concrete examples and distinguishes from sibling tools like get_indicator and get_series, making the purpose 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?

The description explicitly states that the tool is 'designed for deep-research connectors' and advises to use get_indicator/get_series for richer control. It also notes that returned IDs can be passed to fetch, providing clear usage guidance and alternatives.

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, idempotentHint, and destructiveHint false. The description adds useful behavioral context: it returns indicator keys with units and source notes, and it covers specific data sources (World Bank, IMF, DBnomics). No contradiction with annotations.

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 two sentences and every phrase adds value: sources, example topics, return type, and downstream usage. It is front-loaded with the main action and avoids filler or repetition.

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 single-parameter search tool without an output schema, the description adequately explains what it returns (keys, units, source notes) and its data coverage. It does not mention potential limits like result pagination or query behavior, but the description provides enough for an agent to use the tool 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 input schema covers the single 'query' parameter with a description that includes examples ('government debt', 'fx reserves'). The tool description reinforces this with additional example topics, but adds no fundamentally new semantic detail beyond what the schema already 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 names a specific verb ('Search') and resource ('StatCite's curated indicator registry'), lists example topics, and explains that it returns indicator keys usable with other tools. This clearly distinguishes it from generic search tools and establishes a specific functional niche.

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 provides implicit usage context by stating it returns keys 'usable with get_indicator/verify_stat' and lists example topics like inflation and debt. However, it does not explicitly state when not to use this tool or name alternative siblings, leaving the distinction 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?

Discloses the honesty contract ('unverifiable claims come back cannot_verify with the reason, never a guessed verdict'), result ordering, and error isolation ('reports its error in place without sinking the rest of the batch'), which go beyond the readOnlyHint/idempotentHint annotations.

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 longer than necessary but well-structured, front-loading the purpose and then enumerating key behaviors. Every sentence conveys a distinct constraint or behavior, with no fluff.

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 complex batch tool, it covers batching limits, error behavior, output ordering, citation, and honesty contract. The presence of an output schema means return-value details are not required, and the description covers the critical operational aspects.

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 schema already covers all parameters with descriptions (100% coverage), and the description's mention of the claim fields ('Indicator + country + period + claimed value') is a summary rather than new semantics. It doesn't explain tolerance parameters, but they are in 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?

Clearly states the tool's function: 'Fact-check a whole draft or report in one call' and distinguishes it from verify_stat by saying 'instead of calling verify_stat once per figure'. The verb is specific (fact-check) and the resource is a whole draft batch.

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 instructs when to use: 'instead of calling verify_stat once per figure' and provides batch limits ('Accepts 1–15 claims per call... Split larger drafts into multiple calls'). Also clarifies the shared verdict engine with verify_stat.

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?

The description goes well beyond annotations by disclosing the 'honesty contract' (never guessing, returning cannot_verify), fallback behavior under strict_source, and the as_of vintage resolution details. These are critical behavioral traits not captured in readOnlyHint or other annotations.

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 informative but somewhat verbose, with several paragraphs that repeat or expand on schema descriptions. It is front-loaded with the main purpose, but later sections on as_of and fallback behavior are long and could be trimmed. Every sentence earns its place regarding policy, but the length reduces readability.

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?

Given the tool's complexity (8 params, output schema), the description is quite complete: it covers verdict types, diagnostic details, honesty contract, historical vintage resolution, and fallback modes. It does not need to explain return values since an output schema exists, and the description provides sufficient context for an agent to select and invoke the tool 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?

Schema description coverage is 100%, so the baseline is 3. The description adds little beyond the schema for parameters; most parameter-specific details (e.g., as_of behavior, strict_source) are already fully described in the input schema. The description provides a high-level overview but does not enhance or clarify individual parameters further.

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 clearly states the tool's function: 'Check a claimed economic figure... against the official statistical series and get a verdict: match, close, mismatch, or cannot_verify.' This is a specific verb+resource and differentiates it from siblings like verify_claims (likely batch) and compare_sources by focusing on verification against official sources.

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 provides clear usage context: 'Use this before publishing any economic statistic in a report, brief, or article.' It also explains behavior in edge cases (fallback, as_of) but does not explicitly state when not to use it or name alternatives beyond the implicit distinction from sibling tools.

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