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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds behavioral context: it notes that rates change in percentage points, that validation and provenance are included, and lists the full set of statistics. It does not contradict annotations and adds useful nuance beyond the structured fields.

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 structured with a clear purpose statement, a compact list of statistics, and a labeled Args section. It is longer than minimal but each part earns its place, especially the param hints. The front-loading of purpose is effective.

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 14 parameters and no output schema, the description covers the return value ('statistics, validation status and provenance per series') and the addressing method (same as get_data). It does not explain how to choose among the many addressing options (indicator vs. stat_code vs. dataflow), but given the complexity, it provides enough context for an agent to call it correctly, especially with sibling tools available.

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 0%, so the description must compensate. It does: every one of the 14 parameters is explained with a brief type or format hint (e.g., 'concept id or name', 'economy, ISO code or EA', 'ECOS | OECD | IMF | BIS', 'frequency', 'SDMX series key'), and it even notes a dependency ('required with indicator'). This adds substantial meaning beyond the bare 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 ('calculate') and resource ('summary statistics of a series'), and enumerates the exact statistics returned (count, min/max, mean, median, std, CAGR, etc.). It also references get_data for addressing, which helps distinguish it from sibling tools like get_data and compare_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?

The description implies usage when summary statistics are needed, and mentions 'addressed the same way as get_data' which hints at a parallel, but it does not explicitly state when to use this tool over siblings like get_data or compare_series, nor provide exclusions or conditions. Guidance is implicit 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?

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description goes further by explaining the alignment process, aggregation defaults based on flow vs. stock concepts, normalization options, and the return payload (table, correlations, provenance, validation). This exceeds the annotation coverage and gives the agent a full picture of side effects and output structure.

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 lengthy but well-structured with a clear purpose line, three illustrative examples, and a bulleted Args list. Every sentence adds value, and the most critical information (alignment and comparison scope) is front-loaded. It could be tightened slightly, but the organization makes it 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?

Despite no output schema, the description explicitly states what is returned: aligned table, correlations, provenance, validation, and cross-validation where applicable. The examples cover the three main use cases, and all parameters and their effects are described. An agent has everything needed to invoke the tool correctly and interpret results.

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 schema description coverage at 0%, the description carries the full burden. It lists every parameter, explains defaults (e.g., recent_years=3, aggregation rules), and describes the three acceptable series specifications (indicator/country/source, stat_code, or dataflow/key/cycle). It even provides concrete JSON examples. This is exemplary compensation for the sparse 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 verb ('align', 'compare') with a clear resource ('2-6 series') and scope ('across economies, institutions or concepts'). The description distinguishes itself from siblings like get_data and calculate_statistics by focusing on comparison and cross-validation. Examples reinforce the purpose without ambiguity.

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 explicit usage scenarios via three example types (economies, institutions, concepts) and explains the automatic cross-validation when the same concept comes from different sources. It does not explicitly state when not to use it or name alternative tools, but the context is clear enough for an agent to infer appropriate use.

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, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds behavioral detail about the return content (concept, sources, glossary, methodology, tables), which enriches what the agent can expect beyond the annotations. No contradictions.

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 compact and well-structured: a one-sentence purpose, then a returns summary, then an Args block with examples. Front-loaded with the core purpose and no wasted words.

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 tool with four parameters and no output schema, the description explains all parameters, provides examples, and lists the return fields. It is complete enough for an agent to call it correctly without further inference.

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 0%, but the description's 'Args' section explains each parameter (term, country, stat_code, language) with examples and defaults. It fully compensates for the missing schema descriptions, providing meaning beyond the raw property names.

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 ('explain') and resource ('indicator'), and specifies what it returns: concept definition, source mappings, and for Korean statistics, glossary, methodology, and tables. This clearly distinguishes it from siblings like get_data or get_metadata.

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 contextual hints (e.g., 'for Korean statistics') but does not explicitly state when to use this tool versus alternatives like search_statistics or get_metadata. No exclusions or when-not-to-use guidance is provided.

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 only declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description goes far beyond this by specifying validation checks (country, frequency, unit, etc.), cross-validation semantics (MATCH/DIFFER/UNRESOLVED), date conversion rules ('2024', '2024-03', '2024Q1'), default windows (3 months daily, 2 years otherwise), transform behavior, rebase semantics, and the prefer_latest truncation behavior. This is rich behavioral context that directly informs agent expectations. 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?

Although long, the description is meticulously organized: a one-line statement, three numbered access patterns, a bullet list of validation/transformation behaviors, an Args list with short explanations, and a Returns section. Every sentence adds functional value and there is no redundant repetition. The critical usage patterns are front-loaded, so an agent can grasp the core quickly without reading the entire parameter list.

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 24 parameters, no output schema, and no parameter descriptions in the schema, the description carries an enormous burden. It meets this by documenting every relevant behavior, the return structure (series, provenance, validation, optional cross_validation), and providing concrete value examples. The three access patterns cover all major invocation routes, making it fully complete for an agent to call correctly without external documentation.

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 provides zero descriptions (0% coverage) and no enums, so the description is the sole source of parameter meaning. It explains each argument with concrete examples and usage notes: indicator and country are required together, source defaults described, stat_code and dataflow formats are exemplified, and flags like cross_validate and prefer_latest are explained. This fully compensates for the schema's silence.

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 precise statement of purpose: 'Retrieve a time series in the canonical model, with validation and provenance.' It then enumerates three distinct calling conventions (concept, ECOS table, SDMX dataflow), each with concrete field requirements. This clearly distinguishes the tool from siblings like search_statistics (which searches concepts) and get_metadata (which presumably fetches metadata).

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 explicit routing logic: 'Korea uses ECOS first; other economies OECD, IMF and BIS. If a source has no data, the next one is tried.' It also lists validated access patterns and optional cross-validation, giving the agent unambiguous choices for how to invoke the tool. While it doesn't explicitly contrast with siblings, the level of procedural detail (argument combinations, fallback behavior) functions as strong usage 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 indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral context beyond annotations by detailing source-specific behavior, the series-key format (e.g., 'M.US'), and the output_format='sdmx' effect for ECOS. It supplements the annotations without contradicting them.

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 tightly organized: a one-sentence purpose statement, two concise source-specific behavior bullets, and a clean parameter list. Every sentence adds value—the series-key example is particularly illustrative without being verbose. No filler or redundant 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?

Given there is no output schema, the description adequately explains returns ('dimensions, codes per dimension, a key template') and covers the special output_format behavior. It also addresses both usage modes and parameter semantics. It stops short of detailing error conditions or required-parameter validation, but for a read-only metadata lookup tool, the coverage is sufficient for correct 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?

Schema description coverage is 0%, so the description is the only source of parameter meaning. It compensates thoroughly with an Args list that explains every parameter, including acceptable values (source, output_format), examples (stat_code '901Y009', dataflow 'BIS:WS_CBPOL(1.0)'), and cross-parameter interactions. This is essential and well-executed.

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: 'Return the structure (dimensions and codelists) of a dataset', and explicitly ties its purpose to 'to find the codes get_data needs.' This clearly differentiates it from sibling tools like get_data and search_statistics, making the tool's role obvious.

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 contextual guidance: use this tool to obtain dimension/codelist codes before calling get_data. It explains the two distinct usage modes (OECD/IMF/BIS with source+dataflow, ECOS with stat_code) and gives concrete examples. However, it does not explicitly discuss when not to use the tool or how it compares to alternatives like search_statistics or explain_indicator, so it stops short of full exclusion 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 readOnlyHint, destructiveHint=false, and idempotentHint, so the description doesn't need to repeat safety. It adds valuable behavioral detail such as how dataflows require every word to match the English name/id, tables without query return children of parent_code, and key_statistics returns latest values. This goes beyond annotations without contradicting them.

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 well-structured with a one-line summary, a scope section, an Args list, and a Returns note. It is a bit long but every bullet adds necessary detail. It is front-loaded with the purpose and avoids 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?

For a search tool with no output schema, the description covers the main aspects: what each scope searches, how parameters affect results, and that results are returned per category. It lacks detail on the exact fields of each result item, but this is a minor gap given the tool's exploratory role.

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 0%, so the description fully compensates by explaining all seven parameters with examples and context: query gives example terms, scope enumerates all valid values and meanings, source specifies institutions, parent_code, searchable_only, limit, and language. This is far more than the bare 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 clearly states the tool searches concepts, OECD/IMF/BIS dataflows, and ECOS tables/items, and explicitly labels itself as 'The first step before retrieval,' which distinguishes it from sibling retrieval tools like get_data. The verb and resource are specific, and the scope section adds granularity.

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 says it is the first step before retrieval, implying use before get_data, and for concepts it even specifies how to retrieve with get_data. However, it does not explicitly list when not to use it or name all alternative tools, though the scope definitions provide clear context for choosing scopes.

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