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 the action-specific parameter requirements, but it does not disclose response format, pagination, or potential errors. Given that annotations cover the safety profile, the description adds only marginal behavioral context beyond the action list.

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 clear introductory sentence and a bulleted list of actions. It is front-loaded with the purpose. The dataset list is somewhat redundant with the schema's parameter description but still useful. No unnecessary words; it earns its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains all four actions and their parameter requirements, which is useful. However, since there is no output schema, the description should describe what each action returns (e.g., lists of datasets, parameter names, values). It only implies this via the action names. For a tool with multiple actions and no output schema, this is a notable gap.

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 descriptions for each parameter, so baseline is 3. The description adds value by mapping each action to its required parameters (e.g., 'list_parameters requires dataset_name') and by listing valid dataset names. This clarifies the usage of parameters beyond the schema's individual descriptions.

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: 'Discover BEA datasets, parameters, and valid parameter values.' It lists all four actions with their exact functions, making it unambiguous what the tool does and how it differs from data-retrieval siblings like bea_gdp_national.

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 says it is 'Essential for exploring the BEA API before making data requests,' which signals when to use it. It does not name specific alternative tools, but the context strongly implies it is a precursor to data-fetching tools. No exclusions are given, but the usage context is 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: annual frequency, release timing, and concrete table names with meanings. It does not mention output format or pagination, but that is a minor gap given the low-risk read-only nature.

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 front-loaded: the purpose appears in the first line, followed by essential scope, update cadence, and table examples. Every sentence earns its place, and the structure makes key facts scannable. No filler or redundant 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?

For a read-only tool with two optional parameters Asiatic, the description supplies defaults, valid table examples, data coverage, temporal frequency, and a pointer for discovering more tables. No output schema exists, but an agent likely needs no more than this to make a correct call. A slight gap is the lack of any hint about the response shape, which would otherwise make this a 5.

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 describes both parameters at 100% coverage, including defaults and the year format. The description adds meaning by enumerating common table names and what each one represents (e.g., FAAt101 current-cost net stock by type). This goes beyond the schema's generic 'table name' description, so the definition adds useful semantic value.

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 clear verb-object pair: 'Get Fixed Assets data — net stock, depreciation, and investment tables.' It names the specific resource and scope, listing common table identifiers and data categories. This distinguishes it from sibling BEA tools like GDP or international transactions without requiring schema inspection.

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 sets clear context: annual data only, update cadence, and data coverage (private/government fixed assets, equipment, structures, IP products). It directs the agent to bea_dataset_info for table discovery, which serves as an alternative lookup path. However, it does not explicitly state when not to use this tool versus other BEA datasets, so it stops 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 this a read-only, idempotent operation, so the bar is lower for behavioral disclosure. The description adds meaningful defaults (default table 1, industry ALL, default year range) and clarifies that 'Industry='ALL' returns all sectors,' which goes beyond what the schema states.

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 front-loaded, with the primary action in the first sentence and the table/industry options in an easy-to-scan list. No redundant elaboration or filler.

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 query tool with four optional parameters and no output schema, the description covers the key choices: table ID, industry scope, and national focus. It omits output shape/pagination, but the annotations plus thorough schema make the missing information minor.

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 schema already explains year, industry examples, table_id values, and frequency. The description adds minor value by listing TableID options and noting that ALL returns all sectors, but largely restates schema content.

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 verb and resource: 'Get GDP contribution by industry sector nationally from BEA GDPbyIndustry dataset.' This clearly differentiates the tool from nearby BEA siblings like bea_gdp_national (national totals) and bea_gdp_by_state (state-level data).

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 scope is clear: national-level GDP by industry. However, the description never names alternatives such as bea_gdp_by_state or bea_gdp_national or states when to prefer one over another. Usage context is implied by the tool's scope but not explicitly enforced.

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, so the safety profile is covered. The description adds some contextual value by naming the dataset family and table variants, but it does not disclose return format, units, or any boundaries beyond what the schema already states.

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 and clearly structured: it leads with a one-sentence purpose, then uses compact labeled lists for table options and GeoFips. There is no filler or redundant narrative, and each line adds useful selection detail.

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?

The schema plus description together cover the query options and defaults, and the annotations cover the behavioral safety profile, so an agent can reasonably invoke the tool and know what kind of data it returns. It could be even more complete by mentioning units and explicit sibling differentiation, but these gaps are not blocking for a read-only lookup tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters meaningfully. The description repeats table and GeoFips details but does not add fundamentally new semantic information beyond what is in the parameter descriptions, so the baseline of 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 clearly states the tool's purpose: 'Get gross domestic product for U.S. states from BEA Regional dataset.' It combines a specific verb, resource, and geographic scope, and the table options further clarify that it serves state-level BEA data rather than national or industry GDP queries.

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 gives useful within-tool guidance by listing table options and explaining GeoFips, and the phrase 'for U.S. states' implies its primary use. However, it never explicitly contrasts this tool with sibling tools like bea_gdp_national or bea_gdp_by_industry, nor provides when-not-to-use information.

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, so the safety profile is established. The description adds useful behavioral context by explaining what data is shown and mapping common NIPA table names to their contents. No contradiction with annotations is present.

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 clear one-sentence summary followed by a scannable bullet-style table list. It contains no filler, though some table details duplicate the schema descriptions.

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 required parameters and no output schema, the description plus schema covers the main invocation decisions: table, year, and frequency. It could be slightly more complete by pointing to related BEA tools for state or industry data, but that is not essential for calling this 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 value beyond the schema by pairing table IDs with readable meanings, including extra detail like T10106 nominal GDP, T10111 percent change, and T30100 government receipts, helping an agent choose table_name more confidently.

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 it 'Get[s] U.S. national GDP data from the NIPA tables' and enumerates the covered series: GDP, GDP growth, components, and deflators. It also lists specific table names, which makes the tool's purpose unambiguous and distinguishes it from state-level and industry-level BEA siblings.

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 intended scope explicit: national GDP and NIPA tables, and gives a table catalog that helps an agent choose table_name. It stops short of explicitly naming alternatives like bea_gdp_by_state or bea_gdp_by_industry, so it provides clear context but no explicit 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 readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds minimal behavioral context—only that it 'shows interrelationships,' which is more about content than behavior. It does not disclose pagination, rate limits, or return format, but with annotations covering safety, a score of 3 is appropriate.

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 concise sentences with no wasted words. It front-loads the core purpose, adds a brief explanation of the data, and ends with a practical pointer for parameter discovery. It is well-structured and 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 simple tool with two well-documented parameters, no output schema, and annotations covering safety, the description is nearly complete. It explains what the tool does, points to the discovery mechanism for table IDs, and indicates the data covers interrelationships. It could mention that output is tabular, but the absence of an output schema and the tool's straightforward nature make this a minor gap.

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 provides descriptions for both parameters: year supports comma-separated values or 'ALL', and table_id requires discovery via bea_dataset_info. The description repeats this discovery hint, adding no new semantic meaning beyond the schema. Given 100% schema coverage, the baseline is 3, and the description does not exceed that.

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 retrieves Input-Output statistics, specifically Make, Use, and Requirements tables, and explains they show interrelationships between U.S. producers and users. This distinguishes it from other BEA tools like GDP or personal income. It lacks an explicit comparison to sibling tools but the name and content make its 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 provides a clear pointer to bea_dataset_info for discovering table IDs, which is a useful prerequisite. However, it does not explicitly state when to use this tool versus other BEA tools, nor does it mention any exclusions or alternative scenarios. The guidance is limited to a discovery step, not a full decision framework.

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 establish read-only, idempotent, non-destructive behavior, so the description adds meaningful context beyond them by explaining what IIP represents and by defining component semantics such as 'ChgPosTrans' (change from transactions), 'ChgPosPrice' (price changes), and 'ChgPosXRate' (exchange rates). It does not cover response shape or API quirks, but the annotation coverage lowers the burden.

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 front-loaded purpose sentence, a one-line conceptual clarification, and short bullets for key parameter values. There is no filler, and the most decision-relevant information appears first.

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 optional parameters and no output schema, the description is nearly complete: it states defaults, provides valid example values, and points to bea_dataset_info for the full TypeOfInvestment list. The main gap is that the return format/columns are not described, but the parameter space is well covered by the schema and description combined.

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 extra value by giving meaningful TypeOfInvestment examples with plain-language meanings and by expanding Component values into their economic meanings beyond the schema's option list. Year and frequency are left to the schema, which already documents them adequately.

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?

Opens with a specific verb and resource: 'Get U.S. international investment position (IIP) data.' The second sentence clarifies that it returns end-of-period accumulated stocks of assets and liabilities, which distinguishes it from flow-oriented siblings like bea_international_transactions or bea_intl_services_trade. This is enough for an agent to know exactly what this tool provides.

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 by defining the data domain ('end-of-period accumulated stocks'), which suggests it is appropriate for position/stock questions. However, it never explicitly states when to use this tool versus alternatives such as bea_international_transactions or bea_dataset_info, and it gives no exclusions or fallback 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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it explains the data covers transactions between U.S. and foreign residents, lists default indicator (BalGds), and clarifies frequency options. It does not mention pagination or response format, but for a read-only data retrieval tool this is acceptable.

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 clear opening sentence, a brief explanation of what the data tracks, and a bulleted list of indicator examples. It is slightly longer than necessary but every section earns its place. The frequency line is concise and useful.

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 data retrieval tool with 100% schema coverage and no output schema, the description is largely complete. It explains the data scope, provides indicator examples, and notes that bea_dataset_info can be used for the full list. It could mention that 'All' for area_or_country returns all breakdowns, but the schema already covers that. The lack of an output schema is not a major gap for this type of tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all four parameters. The description adds value by explaining the meaning of the data categories (e.g., BalGds = balance on goods) and the default values, but it does not add significant new semantics beyond the schema. 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 clearly states the tool retrieves U.S. international transactions (balance of payments) data, with a specific verb ('Get') and resource. It lists concrete indicator examples and frequency options, distinguishing it from other BEA tools like bea_gdp_national or bea_intl_services_trade. 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?

The description provides clear context on what data the tool returns and includes indicator examples, but it does not explicitly state when to use this tool versus alternatives like bea_intl_services_trade or bea_international_investment. The sibling list includes several BEA tools, so explicit exclusion guidance would improve this dimension.

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 safety profile is covered. The description adds the crucial behavioral requirement that BEA mandates a specific TypeOfService or AreaOrCountry, and clarifies that data is annual. It does not mention pagination or response format, but given the annotations, this is adequate.

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-organized: an opening one-liner defining the tool, an IMPORTANT note front-loaded for critical usage guidance, followed by compact parameter value lists. No redundant sentences; every line contributes to correct usage.

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 5-parameter tool with no output schema registering, the description covers all parameter semanticships, including defaults and allowed values. It also points to a sibling tool (bea_dataset_info) for exhaustive value discovery. The only missing piece is a description of the return format, which is not strictly required for invocation but would have been useful. Overall, the description is sufficient for an agent to call this 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 coverage is 100%, so the baseline is 3. The description goes far beyond the schema by listing plausible enum values for type_of_service, trade_direction, and affiliation, including examples like 'Telecom', 'Travel', 'Comp', and 'ChargesForTheUseOfIpNie'. It also explains the interdependency between type_of_service and area_or_country, which is not present in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Get'), a clear resource ('U.S. international trade in services data'), and a temporal scope ('annual'). This clearly differentiates it from sibling BEA tools like bea_international_transactions or bea_gdp_national, even 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?

Explicitly warns about the critical constraint: 'You cannot use ''All'' for both simultaneously' when selecting TypeOfService and AreaOrCountry. It also directs users to bea_dataset_info for discovering valid values and lists acceptable values for multiple parameters. This is clear, actionable 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds contextual detail about the data coverage (Outward/Inward/State/Parent) and the meaning of ownership levels, which goes beyond annotations but does not describe return formats, pagination, or rate limits. 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 compact and well-organized, using bullet lists for the required dimensions and a brief note for AMNE-specific flags. It is front-loaded with the core purpose, and every sentence contributes meaningful guidance without 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?

With 9 parameters, 3 required, conditional dependencies, and no output schema, the description covers the most important semantics for correct invocation: required parameters, valid values for Direction and Classification, and AMNE-specific flags. Minor gaps remain, such as year format and advanced use of series_id, but these are documented in the schema's parameter descriptions.

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 baseline is 3, but the description adds meaningful semantics beyond the schema: it explains what each DirectionOfInvestment value means (e.g., 'Outward': U.S. investment abroad / foreign affiliates) and clarifies which classification options are relevant for AMNE. It also explains the meaning of ownership_level and non_bank_affiliates_only values, raising the score above baseline.

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 identifies the tool as retrieving Direct Investment (DI) and Activities of Multinational Enterprises (AMNE) data, with a specific verb and resource. It enumerates the main dimensions (DirectionOfInvestment and Classification). However, it does not explicitly differentiate this tool from sibling BEA data tools, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides conditional usage guidance, such as setting ownership_level and non_bank_affiliates_only for AMNE stats, and notes which Direction values are AMNE-only. It implies when the tool is appropriate but gives no explicit alternatives or exclusion criteria for choosing a sibling dataset tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds a useful data-quality caution (lower quality than aggregates) and hints at table selection, which goes beyond the annotations. It does not describe response format or pagination, but given the annotations' coverage, this is acceptable.

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 and well-organized: it states the core purpose first, adds a caution, then lists common tables and a discovery tip. No filler or redundant sentences, and it is front-loaded with the most important information.

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 3 optional parameters, no output schema, and a clear sibling set, the description provides enough to call it correctly: it explains the data scope, gives examples, and points to discovery. It could be improved by mentioning the response format, but the absence is not critical given the annotations and the tool's simple parameter set.

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 schema documents each parameter. The description adds value by listing common tables and instructing users to use bea_dataset_info for discovery, which directly aids the table_name parameter. This extra context raises it above the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Get') and resource ('NIPA underlying detail data') and adds a clarifying phrase ('more granular national account breakdowns') that differentiates it from sibling BEA tools like bea_gdp_national which likely provide aggregates. It also lists common tables, making its purpose unmistakable.

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 context by explaining the tool returns underlying detail and warns that these are lower quality than published aggregates, implying that for aggregates one should use other BEA tools. It also directs users to bea_dataset_info for discovering all tables. However, it does not explicitly name alternative tools or state when not to use this tool, 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 readOnlyHint, idempotentHint, and destructiveHint false, covering safety and idempotency. The description adds no further behavioral context such as rate limits, auth requirements, or error handling, but it does not contradict annotations. With annotations covering the safety profile, a baseline of 3 is appropriate.

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 and well-structured. It starts with a clear purpose statement, then uses bullet points to list table options and line code mappings. No redundant information, and the key details are front-loaded.

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?

The description provides enough context for a simple data retrieval tool: it explains the available tables and line codes. It does not describe the output format, but given the lack of an output schema and the simplicity of the operation, this is not a critical gap. Annotations cover safety, so the description is largely complete for calling the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description repeats and organizes the line code and table information that is already in the schema, adding marginal value by presenting it more clearly. It does not provide significant new meaning 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 clearly states the tool's function: 'Get personal income data by state from BEA Regional dataset.' It specifies the resource (personal income data) and the scope (by state), and distinguishes it from sibling BEA tools like bea_gdp_by_state by focusing on income rather than GDP. The table options further clarify what the tool returns.

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 implicitly conveys when to use this tool (when personal income data is needed) but does not explicitly mention alternatives or exclusions. However, the tool name and description make it clear this is for income data, not other economic indicators, so an agent can infer the appropriate context without explicit 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=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by disclosing the BEA caution about lower data quality for these detailed estimates, which is not implied by the annotations. It also mentions the annual-only and start-year constraints, which are behavioral limits. This is useful beyond the structured metadata, though it doesn't discuss pagination or return format, which are not required given the simplicity.

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 succinct sentences, each serving a purpose: identifying the resource, stating data scope, and warning about quality plus directing to helper tool. It is front-loaded with the most important info and contains no filler. Perfectly sized for an API tool description.

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 simplicity (3 params, no output schema, annotations covering safety), the description covers all essential aspects: purpose, differentiation from sibling, usage constraints (annual, start year), data quality caution, and parameter discovery guidance. An agent can confidently invoke this tool correctly with the information provided.

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 all three parameters (year, industry, table_id) have basic descriptions. The description adds significant context: it specifies that data is annual-only and starts from 1997, which directly constrains the 'year' parameter beyond the schema's generic description. It also points to bea_dataset_info for valid TableIDs and Industry codes, which is practical guidance for parameter values. This goes beyond mere schema repetition, earning a 4.

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 'Get' and the resource 'Underlying GDP by Industry', and immediately distinguishes it from the main GDPbyIndustry dataset by highlighting 'more industry detail'. This makes it easy for an agent to know exactly what this tool retrieves and how it differs from the sibling tool bea_gdp_by_industry.

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 explicit usage conditions: 'Annual data only' and 'starting from 1997' establish when this tool is appropriate (and implicitly when not, e.g., if quarterly data is needed). The instruction to 'Use bea_dataset_info to discover valid TableIDs and Industry codes' gives a clear pathway for parameter selection. It also implies that this tool is preferred when more detailed industry data is required compared to the main GDPbyIndustry dataset.

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 the safe read-only behavior is covered. The description adds minimal extra behavioral context—just that it shows categories driving inflation—but nothing about data granularity, update frequency, or output structure. Given the annotation coverage, this is adequate but not rich.

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 concise sentences, front-loaded with the primary purpose and followed by a meaningful outcome ('Shows which categories are driving inflation'). No filler or redundancy; 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?

For a simple read-only tool with two optional params and no output schema, the description gives enough context about what it does and the kind of output (component breakdown). It doesn't mention frequency or index units, but the schema covers parameter defaults and the annotations cover safety. This is reasonably complete for an agent to invoke 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%, with both start_year and end_year clearly documented in the schema. The description adds no parameter-specific meaning beyond the schema, so 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 states a specific verb and resource: 'Get a breakdown of Consumer Price Index by component', listing examples (food, shelter, energy, medical care, transportation). This clearly distinguishes it from BLS siblings like bls_series_data (generic series retrieval) and bls_employment_by_industry (employment focus). The purpose is unambiguous and scoped.

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 an agent needs CPI component breakdowns, especially 'which categories are driving inflation'. However, it does not name any sibling tools or provide explicit when-to-use vs. when-not-to-use guidance, leaving some inference to the agent.

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 the safety profile is covered. The description adds only the behavioral hint that it indicates growing/shrinking sectors, but doesn't disclose output format, time unit, seasonality, or data limitations. This is acceptable but minimal given the annotation coverage.

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 with zero filler. The primary action is front-loaded, and the secondary insight about growth/shrinkage adds value without bulking the text. 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?

This tool has no output schema, so the description carries the burden of explaining what the agent can expect. It mentions 'growing or shrinking' but not the actual return fields, sector naming conventions, or whether results are time-series or a single snapshot. With only 2 optional parameters and a safe annotation profile, the description is functional but leaves moderate room for agent uncertainty.

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 both start_year and end_year described in the schema (including defaults). The description adds no parameter-specific meaning, not even mentioning that a date range can be specified. Baseline 3 is appropriate because the schema fully documents the parameters, and the description doesn't need to repeat them, though it could have enriched them.

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 ('Get'), a clear resource ('employment numbers'), and the breakdown dimension ('major industry sector'). It also adds an interpretive angle ('Shows which sectors are growing or shrinking') that distinguishes it from generic series tools like bls_series_data or bls_cpi_breakdown, making the tool's purpose immediately 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 implies usage through its resource specificity ('employment by industry') but does not explicitly say when to prefer this tool over alternatives such as bls_series_data or bea_gdp_by_industry. There are no exclusionary statements or alternative tool mentions, leaving the agent to infer the selection criteria from the resource name alone.

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, covering the safety profile. The description adds context that the tool returns curated 'popular' IDs, implying a limited set rather than exhaustive coverage. This helps the agent understand the tool's scope. There's no contradiction with annotations, and the added value is meaningful but not extensive.

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 efficient: two sentences and a topic list. The purpose is front-loaded, the rationale is brief, and the topic enumeration is necessary for parameter completeness. There is no waste or verbosity, making it easy to parse quickly.

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 lookup tool with 2 parameters (one optional) and no output schema, the description is nearly complete. It clearly states it returns series IDs, and the topic list covers all valid values. The only missing piece is an explicit connection to follow-up tools like bls_series_data, but that is inferable. Overall, an agent can correctly invoke this tool with the information provided.

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 both parameters (topic and state) are already documented with clear descriptions. The tool description repeats the topic list and mentions state-level data, but adds no new meaning beyond the schema. With high coverage, the baseline of 3 is appropriate; the description doesn't compensate for anything missing.

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 ('Look up'), the resource ('popular BLS series IDs'), and the scope ('by topic'). It distinguishes itself from sibling tools like bls_series_data (which fetches data for a given ID) and bls_employment_by_industry (which provides breakdowns) by focusing on curated ID lookup. The purpose is immediately understandable and 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?

The description explains why this tool exists ('BLS doesn't have a search API, so this provides curated series IDs') and lists valid topics. It implicitly guides the agent to use this tool to obtain series IDs before fetching data, but it does not explicitly exclude alternatives or state when not to use it. The context is clear enough, but exclusions are left to inference.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful scope context (data categories and frequencies) but does not disclose behavioral traits like rate limits, API key advantages, or response shape. 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 front-loaded with a clear purpose sentence, followed by scannable bullets of example IDs and prefixes. It is longer than strictly necessary, but every bullet earns its place by aiding series ID selection, and the structure is easy to parse.

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 partially covers return expectations ('monthly/quarterly/annual observations') but not the response structure (e.g., year/period/value fields). It also does not point to bls_search_series for unknown IDs, and the 10/20-year range limitation lives only in the schema, not the description. These gaps keep it from being fully 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 real value by mapping series ID prefixes (CES, LNS, CU, WP, OE, JT) to data categories and providing six concrete example IDs, which helps an agent construct valid series_ids beyond the schema's generic 'comma-separated BLS series IDs'.

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') with a clear resource ('time series data from the Bureau of Labor Statistics') and states the return content (monthly/quarterly/annual observations for employment, wages, prices, and more). It is distinct from generic list tools but does not explicitly name sibling tools like bls_search_series or bls_cpi_breakdown, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The popular series IDs and prefix table imply this tool is for fetching known BLS series by ID, which is useful context. However, there is no explicit when-to-use vs. alternative guidance—no mention that bls_search_series should be used to discover IDs, or that bls_cpi_breakdown covers subcomponent breakdowns. Clear context but no exclusions.

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, so the description does not need to restate safety. It adds scope facts ('monthly data by port, state, measure type') but nothing about response format, pagination, rate limits, or other behavioral traits.

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 tight sentences immediately state the primary resource and key coverages with no filler. The most identifying information is front-loaded, so an agent can quickly understand the tool and its scope.

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?

All five parameters are optional and fully described in the schema; the description gives the data scope and expected dimensions. Although there is no output schema or explicit mention of defaults/date range, the intersection of description and schema is sufficient to call 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 schema already documents every parameter. The description reinforces that filtering is by port, state, and measure, but it does not materially enrich the individual parameter meanings beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource ('border crossing data at U.S. ports of entry'), lists relevant crossing types, and identifies geographic coverage. This clearly distinguishes it from the broader BTS transport-statistics sibling and other datasets.

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?

No when-to-use or when-not-to-use guidance is provided, and no alternative sibling tool is mentioned. The description only states what the tool covers, leaving an agent to infer when to choose it over nearby tools like bts_transport_stats.

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 idempotentHint=true, covering the safety profile. The description adds historical depth (data back to 1947) and lists data categories, providing useful context. However, it does not describe response structure, pagination, or any specific behavior beyond what annotations already imply, so it adds moderate but not rich transparency.

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 clear opening statement and a bulleted list of indicator categories. It is slightly long but appropriate given the breadth of data covered. The purpose is front-loaded, and there is no redundant information.

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 and only three simple parameters, the description gives a good sense of data content but lacks explicit return format or clarification on whether all indicators are returned together. The absence of an indicator selection parameter is a potential gap that could confuse an agent about how to request specific series. Given the simple parameters, this is a moderate gap.

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 all three parameters (limit, start_date, end_date) are well-documented in the schema itself. The description adds no additional parameter semantics, so it does not go 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 clearly states it retrieves monthly transportation statistics and enumerates specific indicator categories (airline, transit, rail, truck, etc.), giving a precise sense of the resource. It distinguishes itself from other domain tools by its focus on transportation, though it does not explicitly differentiate from the sibling bts_border_crossings, which is a subset of this data.

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 no guidance on when to use this tool versus alternatives like bts_border_crossings or other statistical tools. It lacks any mention of exclusions, conditions, or selection criteria, leaving the agent to infer usage based solely on the title and content.

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 the safety profile is fully covered and the description is not obligated to restate it. The description adds value by disclosing full-result semantics ('all' ceiling rates and 'all' labor categories, not aggregated or filtered). However, it fails to disclose pagination behavior despite a page_size parameter defaulting to 100, which creates ambiguity around how 'all' results are delivered.

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 totaling roughly 30 words, with the primary action front-loaded in the first sentence. There is minor redundancy ('Get all ceiling rates...' vs. 'Shows all labor categories and rates...' both convey the return content), which prevents a perfect score, but the text is otherwise tight and free of filler.

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 tool with one required parameter and annotations carrying the safety burden, the description covers the essentials of what the tool returns and the key input. However, with no output schema, the description is the only source of return-structure information, and it gives only a vague sense of the result format; it also leaves the interaction between 'all ceiling rates' and the default page_size of 100 unexplained, which an agent needs to call it correctly at scale.

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 both parameters are already documented with examples ('GS10F0303V', 'GS35F0581X') and defaults. The description echoes the contract number concept but adds no meaning beyond the schema — page_size is not mentioned at all. Baseline 3 applies because the schema does the heavy lifting.

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 ('Get'), resource ('all ceiling rates for a specific GSA MAS contract'), and lookup key ('contract number (IDV PIID)'), making the purpose unambiguous and far beyond a tautology. It also clarifies what is shown ('all labor categories and rates awarded under that contract'). However, it does not differentiate itself from the closely related siblings calc_search_rates and calc_suggest, so it stops short of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for a specific GSA MAS contract by its contract number' implies the tool is appropriate when the caller already knows the IDV PIID, which is useful contextual guidance. Yet there is no explicit mention of when not to use it, nor any pointer to alternatives like calc_search_rates when a contract number is unknown. The usage guidance is implied rather than stated, which leaves sibling routing to inference.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds that data is refreshed daily and explains the three search modes (keyword wildcard, exact field match, filters), which are behavioral details beyond the annotations. No contradiction.

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?

Five concise sentences, each with a distinct purpose: purpose, resource, search modes, use cases, data freshness. No fluff and front-loaded with the core action.

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 16-parameter search tool with no output schema, the description provides a complete mental model: what data is searched, how to search it (three modes), why it's useful, and data freshness. The schema handles parameter details, so the description only adds necessary context.

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 covers 100% of parameters with descriptions. The description adds high-level semantics: keyword is wildcard across labor category, vendor, contract; search is exact field match; other params serve as filters. This goes beyond the schema's individual field descriptions.

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 ('Search') and resource ('GSA CALC+ ceiling rates for federal labor categories'), and clarifies it finds awarded hourly rates on GSA MAS professional services contracts. This distinguishes it from sibling calc_contract_rates by focusing on ceiling rates specifically.

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 states useful for market research, IGCEs, and competitive pricing, giving clear context for when to use. Does not name alternatives or exclusions, so not a full 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, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavior beyond those: 'Uses contains matching (2 char min)', which informs the agent of substring matching and the minimum prefix length. This is useful contextual behavior not captured 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?

Three short sentences with no fluff. The primary purpose is front-loaded, followed by the use case, then the matching behavior. Every sentence 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?

Given the simple two-parameter schema, rich annotations, and no output schema, the description covers purpose, usage context, and matching behavior. Nothing an agent needs to correctly call calc_suggest appears to be 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 description coverage is 100%, so the baseline is 3. The description restates the enum fields ('labor categories, vendor names, or contract numbers') but does not add parameter-specific meaning beyond the schema. The 'contains matching' detail is a behavioral trait more than a parameter clarification, so no bump above baseline.

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 'Autocomplete/suggest' with a clear resource ('values for labor categories, vendor names, or contract numbers in GSA CALC+ data'). It also names the downstream consumer calc_search_rates, distinguishing it from siblings like calc_contract_rates without needing to open schemas.

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 this is useful for 'finding exact values to use in calc_search_rates', which tells the agent when to invoke it. However, it does not explicitly state when not to use it or name alternatives beyond the implicit calc_search_rates relationship, so a 4 rather than 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 cover read-only, idempotent, and non-destructive behavior, so the safety profile is established. The description adds useful context with 'quarterly provisional' and grouping by race/ethnicity, but it does not disclose how omitted parameters behave or what data window is returned. There is no contradiction with 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 compact and front-loads the core action and resource before enumerating topics. The first sentence lists several indicators and the second repeats overlapping topic labels, which is a minor redundancy, but the overall structure has no filler.

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 query tool with three optional parameters and no output schema, the description plus schema covers the essentials: the resource, topic choices, and race/ethnicity filtering. It does not describe default behavior when all parameters are omitted or the response shape, but that is a minor gap given the simple schema and openWorldHint.

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 already documents all three parameters with 100% coverage, so the baseline is 3. The description mostly repeats the topic list and names race/ethnicity as a grouping dimension without adding accepted-value details or interaction rules beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening phrase 'Get quarterly provisional birth indicators' states a concrete verb and resource, and the indicator list (fertility, teen birth, preterm, cesarean, low birthweight) makes the tool's scope immediately clear. It is easy to distinguish from CDC mortality/life-expectancy siblings because the topic is specifically birth-related. The enumerated topic values further remove 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?

The description implies use for birth and fertility indicators, but it provides no when-to-use or when-not-to-use guidance and does not reference alternatives such as cdc_life_expectancy or cdc_mortality_rates. An agent must infer the appropriate context from the name and topic list rather than being explicitly directed.

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 the safety profile is covered. The description adds useful context about the data span (1999–2017) and sample causes, but it does not disclose behavioral details like whether causes are ranked, how many causes appear per state/year, or the output record shape. This is moderate value beyond annotations, hence a 3.

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 compact sentences with the purpose front-loaded and no filler. The first sentence states exactly what the tool does; the second adds the time range and representative examples. Every sentence 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?

For a simple, read-only filtered query tool with fully documented parameters and strong safety annotations, the description covers the data source, time range, and example content well enough for an agent to make an informed first call. The main gap is the lack of a stated output shape or ranking semantics, but this is not critical given the tool's simplicity and optional filters.

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%: each parameter (year, limit, state) has a meaningful description, including value ranges, defaults, and guidance to omit for all states/years. The tool description does not add parameter semantics beyond restating the 'by state and year' dimensions, so with high schema coverage the baseline of 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 states a specific verb ('Get') and resource ('leading causes of death in the U.S. by state and year'), giving a clear sense of the tool's function. It is distinct from many sibling tools, but it does not explicitly contrast itself with closely related CDC tools like cdc_mortality_rates or cdc_death_rates_historical, so it stops short of full sibling differentiation.

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?

No guidance is provided about when to use this tool versus alternatives. The description gives data range and examples of causes, but no exclusions, prerequisites, or routing advice such as 'use cdc_mortality_rates for rates per 100,000' or 'use cdc_causes_of_death for ranked cause lists.'

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 indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent already knows this is a safe, non-mutating operation. The description adds a temporal constraint (data through early 2023) and clarifies the state format, which supplements the annotations with useful behavioral context 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 two short sentences, front-loading the core purpose and then providing a key usage detail (state abbreviations). No filler or redundant information; every sentence serves a purpose. It is efficient and to the point.

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 tool with clear schema coverage and no output schema, the description covers the main dataset, time frame, and parameter format. It does not mention pagination or optional output details, but given the simplicity and annotations, the description is sufficient for correct invocation. Missing details like default behavior of limit are minor.

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 both parameters (state and limit) are already described in the schema. The description reinforces the state format but does not add new meaning beyond the schema. The limit parameter is fully self-explanatory in the schema. High schema coverage means the description need not duplicate explanations, baseline 3 is warranted.

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 retrieves COVID-19 weekly case and death counts by state, with a specific time frame (data through early 2023). It uses a specific verb ('Get') and resource ('COVID-19 weekly case and death counts'), and is distinct from siblings like cdc_causes_of_death or cdc_weekly_deaths by specifying the data type and 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 implies usage for COVID-19 data retrieval but does not explicitly state when to use it versus other CDC tools (e.g., cdc_weekly_deaths or cdc_causes_of_death). It provides no conditions for selection or alternatives, leaving the agent to infer based on the data focus.

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, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds useful context about age adjustment and the 120+ year range, but does not mention pagination, rate limits, or other runtime behavior. That is acceptable given the low annotation burden.

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 compact lines: the operation, the allowed causes, and a use-case framing. The '120+ years' phrase slightly repeats 'since 1900,' but it reinforces the long-term trend purpose, so no sentence is wasted.

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 query tool with zero required parameters, full schema coverage, and strong safety annotations, the description provides enough context about data scope and intended use. It does not describe the shape of response rows, but the tool is simple enough that this is not a critical gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter. The description's cause list duplicates the enum and adds no new parameter semantics beyond what is already in the schema. Baseline 3 is appropriate here.

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 verb and resource: 'Get age-adjusted death rates for major causes since 1900.' It also lists the exact cause values, making the tool's scope immediately clear. It does not explicitly differentiate from sibling tools like cdc_mortality_rates, but the historical framing is strong enough to avoid major confusion.

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 phrase 'Great for long-term trend analysis — 120+ years of data' gives a concrete use case and implies the tool is best suited for historical spans. It does not name alternatives or exclusions, so it stops short of a 5, but the intended context is 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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds the data source (BRFSS survey), which is useful. However, it does not describe pagination, default behavior when parameters are omitted, or output format. With annotations covering safety, a 3 is appropriate.

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 core purpose, then the list of types. It's efficient with no fluff. It could be slightly improved by integrating the type list more naturally, but overall it is well-structured.

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 retrieval tool with annotations covering safety, the description is mostly complete. It covers the data source and types. Missing are usage guidelines (when to use vs. other CDC tools) and any note about default behavior when state is omitted (though that's in the schema). It doesn't explain return values, but no output schema exists. Slightly incomplete for agent decision-making.

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% (all parameters have descriptions). The description lists disability types, but this duplicates the schema's description for disability_type. The description does not add extra meaning beyond the schema, so a baseline 3 is warranted.

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 disability prevalence by state and type from BRFSS survey.' It specifies the resource (BRFSS) and the data returned (prevalence). The tool name and description distinguish it from other CDC tools, though it doesn't explicitly call out alternatives, so it loses one point.

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?

There is no guidance on when to use this tool vs. other CDC data tools (e.g., cdc_causes_of_death, cdc_places_health). The description does not mention conditions, exclusions, or alternative tools. Context signals show many sibling tools, so this absence is a notable gap.

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 the safety profile is known. The description adds useful behavioral context beyond annotations: it specifies the data includes death rates by state, sex, race, and age groupaine and the time range. It does not disclose pagination or output format, but given the annotations cover mutation risks, this is a reasonable 3.

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 with no filler. The first sentence front-loads the verb, resource, and time range; the second adds contextual value (breakdowns and use case). Everything earns its place, making it highly efficient.

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, no-required-parameter list tool with rich annotations and a fully documented schema, the description is nearly complete. It covers the core purpose, data scope (year range, breakdowns), and a key use case. It does not detail output format or caveats like data completeness by state, but with no output schema required and annotations covering safety, this is not a significant gap. A 4 is fitting.

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 each parameter (sex, year, limit, state) is documented in the schema. The description adds no new parameter-level meanings, but it does mention 'state, sex, race, and age group' as result dimensions, which indirectly helps interpret the 'state' and 'sex' parameters. Baseline 3 is appropriate because the schema carries the full burden.

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 'get[s] drug poisoning/overdose mortality by state (1999–2016)' with a specific verb, resource, and time range. It explicitly distinguishes itself from other CDC mortality tools (e.g., cdc_mortality_rates, cdc_causes_of_death) by naming drug overdose as the focus, and the additional breakdowns (sex, race, age group) further clarify the scope.

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 context for when the tool is relevant ('Critical for opioid crisis analysis'), which implies a use case. However, it does not explicitly state when to use this tool over alternatives like cdc_causes_of_death or cdc_mortality_rates, nor does it mention any exclusions. This is 'clear context, no exclusions,' earning a 4.

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 the safety profile is covered. The description adds the temporal limitation (data goes through 2018) which is not in annotations and is critical for correct usage. It also points to an alternative for more recent data. It doesn't describe return format, but for a read-only data retrieval tool with no output schema, that is a minor gap.

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, with the core purpose in the first sentence, valid values in the second, and a usage note in the third. It is front-loaded and contains no filler. Every sentence adds value, and the key scoping constraint (date range) is stated early.

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 no output schema, the description implies the result (life expectancy values) but doesn't specify structure. However, the tool is simple and the parameters are well-documented. Annotations cover safety and idempotency. The only missing piece is a note about pagination or response format, but the 'limit' parameter hints at pagination. Overall, sufficient for an agent to call correctly without extra context.

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% – all four parameters have descriptions. The description repeats the enum values for sex and race, but that adds no new meaning beyond the schema. The year range is already in the schema description. The 'limit' parameter is covered by schema. No additional semantic insight is provided beyond what the schema already offers, so 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 states a specific verb ('Get') with a clear resource ('U.S. life expectancy at birth') and scope (by race and sex, 1900–2018). It also lists the exact allowed values for race and sex, which differentiates it from other CDC tools. The final sentence explicitly names the sibling cdc_mortality_rates as the alternative for more recent data, distinguishing it.

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 clearly indicates when to use this tool: when the user needs life expectancy data within the 1900–2018 range. It also explicitly says 'For more recent mortality trends, use cdc_mortality_rates,' giving an alternative and the condition to choose it. This is direct and actionable.

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 the tool read-only, idempotent, and non-destructive. The description adds useful behavioral context by stating the return fields (rate_overall, rate_sex_female, etc.) and the 'provisional' nature of the data, but does not mention pagination behavior or rate limits. It adds 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?

The description is two sentences: the first states the core function with a front-loaded verb and resource, the second lists causes and return fields. No wasted words, well structured.

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?

The description covers the main return structure and data scope, which is sufficient given the absence of an output schema. It doesn't explain pagination or default behavior when parameters are omitted, but these are minor gaps. The read-only, idempotent nature is already annotated, so the description is fairly complete for an agent to call 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 already provides full descriptions for all 4 parameters (cause, limit, quarter, rate_type) with examples and defaults. The description adds no additional parameter-specific information, so it relies on the schema. With 100% schema coverage, the baseline score 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?

The description clearly states the tool retrieves provisional age-adjusted death rates filtered by cause, sex, and state, with a specific time range (quarterly, 2020–present). This distinguishes it from siblings like cdc_death_rates_historical (historical) and cdc_weekly_deaths (weekly).

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 context (quarterly, provisional, 2020–present) but does not explicitly state when to use this tool over alternatives like cdc_death_rates_historical or cdc_query. No exclusions or alternative routing is given, so the agent must infer based on the data granularity.

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, destructiveHint=false, openWorldHint=true, and idempotentHint=true, so the description does not need to repeat safety traits. It adds useful context about the data scope (adult obesity, physical inactivity, fruit/vegetable consumption) and the breakdowns available. However, it does not mention any behavioral nuances such as pagination, default limits, or how the returned data is structured.

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 concise sentences with no fluff. The first sentence states the core purpose, and the second lists the topic values and breakdown dimensions. It is well front-loaded and 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?

For a simple query tool with three parameters and no output schema, the description, combined with the schema and annotations, covers the essentials: what data it returns, the allowed topics, and the optional state filter (via schema). It does not provide an example or clarify output shape, but given the simplicity and the presence of the schema, it is nearly complete. A small gap is the lack of any note about the 'limit' parameter's effect, but that is covered in the schema.

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 description coverage is 100% (all three parameters have descriptions). The description adds no new meaning beyond the schema: the topic values ('Obesity', 'Physical Activity', 'Fruits and Vegetables') are exactly repeated from the schema. According to the rubric, when coverage is high, a baseline of 3 is appropriate, and the description does not go 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 clearly states the specific action ('Get') and the resource (BRFSS data) with the three health metrics. It also lists the breakdown dimensions (state, race, age, income, education) and the topic values, making it distinct from sibling CDC tools like cdc_mortality_rates or cdc_places_health, which cover different indicators.

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?

No guidance is given on when to use this tool versus alternatives. There are many sibling CDC health tools (e.g., cdc_places_health, cdc_life_expectancy), and the description does not mention any exclusions, prerequisites, or comparisons. The topics and dimensions imply usage context, but there is no explicit 'when to use' or 'when not to 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 include 'readOnlyHint: true' and 'destructiveHint: false', so the safety profile is covered. The description goes beyond annotations by explaining the output structure: 'Each row contains ALL measures for a city as separate columns'. This is useful context that annotations don't provide. However, it does not mention pagination behavior, rate limits, or data update frequency, which might be useful. Without those, the score is moderate.

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, with two sentences. The first sentence is informative and front-loads the main purposeches. The second sentence adds a crucial detail about the data structure. There is minimal waste, though it could be slightly more structured with bullet points for the measures. Overall, it is efficient and readable.

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?

The tool is a read-only data retrieval tool with a simple interface (3 optional parameters). The description covers the main purpose, the data scope, and the output format. There is no output schema, so the description's explanation of the row structure is important and provided. The tool is not overly complex, so the description is adequate. Could benefit from noting the default limit behavior (default 200) which is in the schema anyway.

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 all three parameters (city, limit, state) are documented in the schema. The description does not add substantial information about parameters beyond what the schema already states. For example, the description does not explain how to use 'state' with 'city' (e.g., whether state is needed for disambiguation). It mentions examples of city names in the schema, but the description does not enhance this. Since coverage is high, baseline is 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Get'), a specific resource ('city-level health indicators from CDC PLACES'), and the scope (all U.S. cities with population > 50,000). It lists examples of the measures included (obesity, diabetes, etc.). While there is a sibling 'cdc_places_health' which might be related, the description's specification of 'city-level' distinguishes it from the broader 'health' tool. The description is clear enough for an agent to understand what this tool does.

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 does not explicitly state when to use this tool versus alternatives.can be inferred that this tool is for city-level data, while sibling 'cdc_places_health' might cover other geographies, but no explicit comparison is made. It says 'every U.S. city' but does not mention when not to use it or suggest alternatives. The usage context is implied but not explicitly stated.

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, open-world, and non-destructive behaviorikuha. The description adds beyond annotations by stating 'Returns crude prevalence (%) by county' and identifying the data as BRFSS-based estimates. This gives the agent concrete output-format and source-quality context without contradicting 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 front-loaded with the core action and scope, followed by a compact, exhaustive measure list and a single closing sentence about return format. The measure enumeration earns its length because it compensates for the incomplete schema enum; there is no filler.

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 states the return type and unit ('crude prevalence (%) by county'). It fully enumerates available measures and implies filtering through the schema's state/measure parameters. Minor gaps like county identifier format and pagination behavior do not prevent correct 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?

Although schema description coverage is 100%, the description adds value by listing all 27 measure IDs, far more than the schema's truncated measure list. It also clarifies the output unit ('crude prevalence (%)') and the county-level domain. This materially enriches the sparse schema parameter descriptions.

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 'Get county-level health indicators from CDC PLACES', combining a specific verb, resource, and geographic scope. The county-level qualifier distinguishes it from sibling tools like cdc_places_city, and the long measure list makes the data domain unmistakable.

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 clearly frames this as a county-level CDC PLACES indicator tool, which implicitly tells an agent when to reach for it versus cdc_places_city or general CDC query tools. It does not name alternative tools or explicitly state exclusions, but the county-level scope is a strong contextual signal.

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, so the description does not need to repeat that. It adds the list of dataset IDs and their context (e.g., death 1999–2017), which is useful. However, it does not disclose behavior like return format, pagination, or that this is an ad-hoc query tool meant for cases where dedicated tools don't fit.

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: one opening sentence and a list of datasets. The purpose is front-loaded, and the dataset list is dense but necessary. It avoids unnecessary 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?

The description tells the agent which datasets are available and that SODA syntax is used, which is sufficient for a generic query tool. However, it omits guidance about the existence of dedicated tools for the same datasets and does not explain when custom queries are needed. Given the lack of an output schema and the availability of dedicated siblings, this is a moderate gap.

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 all parameters are already documented in the schema with examples. The description adds no parameter-specific meaning beyond what the schema provides, so it meets the baseline for full 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's purpose: a custom query against any CDC dataset using SODA syntax. It lists specific dataset IDs, which makes the resource concrete. It distinguishes itself from dedicated CDC tools (like cdc_life_expectancy) by being generic, though it does not explicitly name those siblings.

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 no guidance on when to use this tool versus the dedicated CDC dataset tools (e.g., cdc_life_expectancy, cdc_mortality_rates). It does not mention alternatives or exclusions. An agent might incorrectly choose this generic tool when a specialized tool would be more 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 declare readOnly, idempotent, and non-destructive. The description adds behavioral context by noting the data is 'provisional' and 'updated weekly,' which implies data may be revised. It also discloses the availability of percent_of_expected_deaths for excess mortality detection, going beyond annotation basics.

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) and front-loads the core action. The all-caps emphasis on data currency is attention-grabbing but not wasteful. Every sentence adds value, and there is 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?

The tool has no output schema, so the description partially compensates by mentioning the percent_of_expected_deaths field. It clearly indicates the scope (weekly, by state, specific causes) and data coverage. However, it does not explicitly describe the full output structure (e.g., fields like year, week, state), which might leave some ambiguity for the agent.

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 all parameters (year, limit, state) are fully documented in the schema. The description does not add any additional parameter-specific meaning; it only mentions a response field. Thus, the baseline of 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 clearly states the tool retrieves weekly provisional death counts by state, specifically for COVID-19, pneumonia, influenza, and total deaths. It also mentions the key extra field percent_of_expected_deaths, making the purpose precise and 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 provides strong context by highlighting that this is the most current CDC mortality data, updated weekly and covering 2020–present. This helps the agent decide when to use this tool over others, though it does not explicitly name alternatives or exclusions.

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 the safety profile is covered. The description adds the ACS data-source context and shortcut positioning, but does not disclose response shape, pagination, or any limitations beyond using the more flexible sibling.

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 short sentences deliver the core function, the data source, and the sibling routing with no filler. The main capability is front-loaded and every clause 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?

For a simple read-only, two-optional-parameter tool, the description plus schema and annotations are nearly sufficient. It only stops short of describing the response format, which is not supplied by an output schema.

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 both year and state are already documented with defaults, ranges, and FIPS examples. The description adds no parameter-specific detail beyond what the schema contains, so the baseline of 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 ('Get') with a concrete resource ('population data for U.S. states') and names the data source ('American Community Survey'). It also distinguishes itself from the more general sibling 'census_query', so an agent can tell when this convenience endpoint applies.

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 frames itself as a 'Quick shortcut' and explicitly routes users who need 'more flexibility' to 'census_query directly'. This gives an if/then choice between the simple tool and its flexible 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?

Annotations already convey readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that it returns data for variables and geography, but it does not disclose response format, pagination, rate limits, or other runtime behaviors. With annotations doing most of the safety work, a 3 is appropriate.

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 front-loaded with the core purpose, then adds examples that are directly useful for invoking the tool. The two 'Common...' lines are well-structured and each carries information, though the phrase 'and more' is a minor vagueness that prevents a 5.

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 query tool with rich schema descriptions and no output schema, the description supplies enough context through dataset examples, variable meanings, and geographic examples. It could be more complete by mentioning response shape or how to discover additional variables, but nothing essential to making a first correct call 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%, so the baseline is 3. The description adds meaningful value by mapping common variable codes to human-readable meanings (e.g., B19013_001E = median income) and by providing realistic dataset paths. This goes beyond the schema's minimal examples, warranting a 4.

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: 'Query the U.S. Census Bureau Data API.' It also clarifies the output ('Returns data for specified variables and geography') and lists supported datasets. It does not explicitly distinguish itself from siblings like census_population or census_search_variables, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by listing common datasets and variable examples, so an agent can infer this is the general-purpose Census data query tool. However, it provides no explicit when-to-use vs. alternatives, and it does not mention sibling tools that might be more appropriate for variable discovery or population-specific lookups.

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the behavioral detail that it returns variable IDs for downstream use, but doesn't disclose output format, pagination, or error behavior. Given the strong annotation coverage, a 3 is appropriate.

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 with zero filler. The purpose is front-loaded, and the mention of census_query immediately signals the tool's role in the pipeline. Nothing extraneous.

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 search tool with three documented parameters and no output schema, the description is complete enough: it states the purpose, clarifies the return value (variable IDs), and points to the downstream tool. It could mention the max_results limit, but that's already in the schema, so the description 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 description coverage is 100%, so the input schema fully documents dataset, keyword, and max_results. The description adds no extra parameter semantics beyond what the schema already provides. Baseline 3 is appropriate when the schema handles all parameter documentation.

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' and the resource 'Census variable names/codes', and explicitly distinguishes its purpose from census_query by noting it returns variable IDs for use with census_query. This makes it obvious this is a discovery tool, not a data retrieval tool, and differentiates it from census_population and census_query.

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 implicitly establishes the usage workflow: use this tool to discover variable IDs, then use census_query to fetch data. This gives clear context on when to call it. However, it doesn't explicitly say when not to use it or mention alternatives like census_population, so it stops short of full exclusions.

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 the aggregation behavior — returning counts grouped by a field — but doesn't disclose response shape, group limits, or whether date filters apply to the aggregation. This is adequate but not rich.

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, with the core behavior front-loaded in the first four words. Every sentence earns its place: the first states what it does, the second gives use cases and enumerates valid fields. 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?

There is no output schema, so the description should help an agent predict the response shape, but it only says 'counts grouped by a field.' Missing details like sorting, limits, or exact result format are absent. It's adequate for a simple call, but an agent would be guessing at response 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 description coverage is 100%, so the schema already documents all parameters and the field enum. The description mostly repeats the enum values and gives example use cases, adding little semantic information 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 clearly states the verb and resource: 'Get complaint counts grouped by a field,' and gives concrete examples of output (product, company, state, issue). It is distinct enough to understand, but it does not explicitly contrast itself with related siblings like cfpb_complaint_trends or cfpb_state_complaints, so it stops short of full differentiation.

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: 'useful for ranking companies by complaint volume, identifying top issues, or comparing states.' This tells an agent when the tool is appropriate, though it doesn't mention when not to use it or point to a preferred 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?

Annotations already cover read-only and idempotent behavior, and the description adds the useful caveat that narrative is returned 'if consented,' disclosing a possible conditional absence of data. This is meaningful behavioral context beyond the schema's parameter definition.

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 with no filler. The primary action and required identifier are front-loaded, and the second sentence economically lists the key return fields.

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 schema, safe read-only annotations, and absence of an output schema, the description provides a reasonable inventory of returned fields and notes the condition on narrative. It is complete enough for an agent to understand the tool's purpose and result shape, though an explicit response format would make it stronger.

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 already provides 100% coverage with a clear description of the complaint_id parameter. The tool description repeats the concept ('by its Complaint ID') but does not add extra guidance about format, provenance, or how to obtain a valid ID, so the baseline score of 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 states a specific verb ('Get full details') and resource ('a specific complaint by its Complaint ID'). This clearly differentiates the tool from the sibling search, aggregation, and trend tools, which operate over sets of complaints rather than a single identified record.

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: call this tool when you already have a Complaint ID and need the full record. It does not explicitly name alternatives or exclusions, but the 'specific complaint' framing implies that search tools should be used to find IDs.

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, covering the safety profile. The description adds behavioral context by stating that the API rejects requests without trend_interval, explaining the required parameter's consequence. It also clarifies lens options and sub-lens drilling, which are behavioral aspects of the aggregation model. It does not mention rate limits or response format, but the annotations lower the bar and the added context is valuable.

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 five sentences with zero fluff. It front-loads the primary purpose, then covers the endpoint, required parameter, lens options, and sub-lens in a logical order. Each sentence earns its place, and there is no repetition of schema information. The structure is tight and scannable.

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 11 parameters and no output schema, the description covers the core aggregation concepts (lens, sub-lens, required interval) and the API's rejection behavior. However, it does not describe the shape of the response (e.g., time series of counts) or the relationship between specific lens and sub_lens values (e.g., which sub_lens are valid for each lens). This is a notable gap, but the schema covers parameter basics and the description provides enough context for an agent to make a reasonable first call.

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 semantic meaning beyond the schema by explaining lens values (e.g., 'overview' for total counts, 'product' for by product) and sub-lens drill-downs, which the schema only labels generically. It also highlights trend_interval as REQUIRED and explains the API's rejection behavior, which is not in the schema. This enhances the agent's understanding of how to combine 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 opens with 'Get complaint trends over time using the CFPB Trends API', clearly stating the verb, resource, and domain. It further distinguishes from siblings by emphasizing the dedicated /trends endpoint and lens-based aggregation, which sets it apart from cfpb_complaint_aggregations, cfpb_complaint_detail, and cfpb_state_complaints. The purpose is unambiguous and 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?

The description implies usage for time-based trend analysis and explains the lens and sub-lens concepts, but it does not explicitly contrast with sibling tools or state when not to use this tool. There is no explicit 'use X instead' guidance, but the focus on trends over time provides a clear contextual boundary. This is adequate but not fully 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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral details beyond these: the fuzzy-search auto-retry for company names, and the explicit statement that it returns individual complaints with company responses. No contradictions with annotations. The description does not describe every edge case (e.g., pagination or rate limits), but for a read-only search tool this is acceptable.

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 composed of five sentences, with the primary purpose front-loaded. The product list is a long but necessary enumeration, and the fuzzy-search example is a concise, useful addition. There is no filler or repetition. Slightly long due to the product list, but justified.

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 optional parameters and no output schema, the description covers the essential context: what the tool does, what it returns, and how filters work. It does not explain the output structure in detail, but since there is no output schema, the description's statement about 'individual complaints with company responses' is adequate. The description also omits pagination/sort details, but those are well-documented in the schema. Overall, it is sufficiently complete for an agent to invoke 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?

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful context beyond the schema: it enumerates the full product list, explains the fuzzy-search behavior for the company parameter, and gives a concrete example ('Wells Fargo' matching 'WELLS FARGO & COMPANY'). These details help the agent use parameters correctly without needing to infer from the schema alone.

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 the CFPB consumer complaint database and lists the main filter dimensions (company, product, state, issue, date, keyword). It also specifies that it returns individual complaints with company responses, which is a clear and specific purpose. However, it does not explicitly differentiate from sibling tools like cfpb_complaint_trends or cfpb_state_complaints, relying on the name and general context.

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 no guidance on when to use this tool versus its siblings. It does not mention alternatives like cfpb_complaint_trends, cfpb_complaint_aggregations, or cfpb_state_complaints, nor does it state what scenarios are better suited for those tools. The only implicit guidance is the mention of 'individual complaints' which hints at its scope, but no explicit 'use this for X, use that for Y' is given.

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds that it returns counts and data per state, which clarifies the output shape, but does not disclose details like pagination or aggregation specifics. This level of additional context is adequate given the annotation coverage.

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 concise sentences with no filler. The primary purpose is front-loaded in the first sentence, and the second and third sentences provide needed context (output type and use cases). Every sentence 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?

Given the absence of an output schema, the description clearly states that it returns compliant counts and data per state, which is essential. It also mentions filter compatibility, covering the main usage context. It does not describe pagination or behavior with no matching data, but for a read-only aggregation tool with annotations covering safety, this is sufficient.

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 each parameter having a description, so the schema already provides full parameter semantics. The description merely mentions the filters are the same as search, which is a helpful cross-reference but adds no new meaning beyond what the schema already conveys. Baseline of 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 states a specific verb ('Get'), an explicit resource ('complaint information broken down by state'), and a clear geographic aggregation. It distinguishes itself from siblings by emphasizing the state-level view, which is unique among CFPB tools like cfpb_complaint_trends (time trends) and cfpb_complaint_detail (individual complaints).

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 context for when to use it ('Useful for maps and state comparisons') and mentions that it applies the same filters as search, implying compatibility with existing search parameters. It does not explicitly name alternative tools or state when not to use it, but the use-case guidance is sufficient.

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=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered structurally. The description adds the database context and the suggestion use case, but it does not disclose behavior such as return shape, ordering, or behavior on no matches—gaps that matter because there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, with the primary function first and the use case second. There is no redundancy with the title or annotations, and every sentence contributes either purpose or usage 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 simple two-parameter, read-only suggestion tool, the description is largely complete: it identifies the resource, the purpose, and the main use case. It could have specified what the suggestion response contains (e.g., just names vs. IDs), but 'suggest company names' and the schema's example values are sufficient for an agent 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?

Schema description coverage is 100%, so both parameters ('text' and 'size') are already documented with examples in the schema. The description adds no parameter-level meaning beyond the schema, so the baseline of 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 names a specific verb ('Autocomplete/suggest') and resource ('company names from the CFPB complaint database'), making the tool's function immediately identifiable. The phrase 'before searching complaints' distinguishes it from cfpb_search_complaints and other CFPB siblings without relying on the title or 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 states a clear when-to-use: 'Useful for finding the exact company name before searching complaints,' which routes an agent to use this as a precondition/normalization step. It does not name an alternative tool or give explicit when-not-to-use conditions, so it falls short of a full 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 destructiveHint=true and idempotentHint=true. The description adds the behavioral effect (forces fresh data on next query) and clarifies the scope of clearing (all or specific source), which complements 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 a single, front-loaded sentence that states the purpose and parameter behavior with zero fluff. Every word contributes 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?

For a simple tool with one optional parameter, annotations covering destructiveness and idempotency, and a fully documented schema, the description provides enough context. It doesn't describe the return value, but no output schema exists and it's not essential for a cache-clearing operation.

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% – the parameter description already lists all valid source values and states that omitting clears all. The tool description adds no new meaning beyond what the schema provides, 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?

The description states a specific verb (Clear) and resource (cached API responses) with a clear goal (force fresh data on next query). It is distinct from all sibling tools, which are data-fetching operations, making this unique and 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 explains when to use it (to force fresh data) and how to scope it (specify a source or omit for all). It does not explicitly discuss alternatives because none exist; the usage context is clear and actionable.

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 the safety profile is well covered. The description adds the behavioral detail that it uses the ClinicalTrials.gov geo-distance filter, which explains the underlying mechanism. However, it doesn't disclose potential limitations like maximum radius, behavior when no trials are found, or whether results are sorted by distance. The description doesn't contradict 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?

Three sentences with no wasted words. The core purpose is front-loaded in the first sentence, the mechanism in the second, and usage guidance in the third. It's appropriately sized for a tool with 7 parameters and clear scope.

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 search tool with 100% schema coverage and no output schema, the description covers the essential context: what it does, how it works, and how to refine results. It could be more complete by noting the default radius (50mi) and that results are paginated, but these are already in the schema. The sibling list shows this is one of several clinical_trials tools, and the description does enough to differentiate it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 7 parameters with examples and defaults. The description adds the conceptual context that latitude/longitude form a search center and that distance is a radius, but this is largely redundant with the schema's parameter descriptions. The description's mention of combining with condition/intervention filters does add some strategic value 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 clearly states the tool searches for clinical trials near a geographic location, using a specific geo-distance filter mechanism. It distinguishes itself from sibling tools like clinical_trials_search (which likely searches by text/condition) and clinical_trials_detail (which retrieves a specific trial). The verb 'search' plus the resource 'clinical trials' and the location-based scope make 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 explains the core use case (find trials near a location) and suggests combining with condition or intervention filters for more specific searches. It doesn't explicitly name sibling alternatives or state when NOT to use this tool, but the context signals and sibling list make the distinction fairly clear. The guidance to combine with other filters is useful but could be more explicit about when to choose this over clinical_trials_search.

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

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

Annotations already cover read-only, idempotent, and non-destructive behavior, so the bar is lower. The description adds valuable behavioral context beyond the annotations: it states that omitting fields returns the full study and that using fields reduces response size, which tells the agent about the request/response trade-off. It does not repeat annotation facts, but it does disclose the filtering behavior.

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 with zero fluff. The first sentence states the purpose, the second lists what data is returned, and the third gives a practical optimization tip. The most important information is front-loaded and every sentence 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?

For a read-only detail tool with only two parameters and no output schema, the description gives a clear picture of what to expect: it names the data sections returned and explains the fields parameter's effect on response size. It does not describe error behavior or output structure, but those are less critical given the annotations and simple parameter set. Overall it is adequately complete 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 100%: both nct_id and fields have clear descriptions in the input schema. The description adds only a minor rationale for the fields parameter ('reduces response size'), which is helpful but doesn't materially expand on the schema's own documentation. Baseline 3 is appropriate because the schema carries the semantic load.

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 verb and resource: 'Get full details for a specific clinical trial by NCT ID.' It then enumerates the returned sections (protocol, eligibility, arms/interventions, design, locations, contacts, oversight), which makes the tool's scope clear and differentiates it from sibling search/stats tools. This is a precise, self-contained purpose statement.

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 this tool is for retrieving full details when an NCT ID is already known ('by NCT ID'), and gives guidance on using the fields parameter to reduce response size. However, it never explicitly tells the agent when to choose this tool over siblings like clinical_trials_search or clinical_trials_stats, nor mentions any exclusions. Usage is implied rather than directly contrasted with 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, covering the safety profile. The description adds that it returns every enum type with all valid values, which is helpful but mostly restates the core function. There's no mention of pagination or response format, but for a simple reference list this is a minor gap.

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 short sentences, front-loaded with the main action, and no redundant phrases. Every sentence adds value: what it does, what it returns, and when to use it.

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 reference tool with one optional parameter fully described in the schemaending no output schema, the description is largely complete. The main missing piece is the exact return structure (e.g., whether it's a flat list or grouped by enum type), but the examples and use case make it clear enough for an agent to call 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 schema description covers the only parameter (enum_type) at 100%, including the filter options and the behavior when omitted. The description itself adds no additional parameter detail beyond the general reference-to-field-values context. Since schema coverage is high, 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 clearly states the tool lists all valid enum values for ClinicalTrials.gov data fields, using the specific verb 'List' with a specific resource. It also names example enum types (Status, Phase, StudyType, InterventionType) and states its purpose as a reference for building search filters. It doesn't explicitly differentiate from siblings like clinical_trials_field_values, but the core purpose 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?

The description provides a clear use case: 'Use as a reference when building search filters or understanding field values.' This tells an agent when to invoke this tool. However, it doesn't explicitly mention alternative tools or when not to use it, leaving some ambiguity relative to similarly-named siblings.

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 the agent knows it's a safe, non-destructive operation. The description adds that it shows min/max/top sizes, but the return format is unspecified (no output schema, no mention of JSON structure), and the default behavior when 'fields' is omitted is only vaguely implied (probably returns stats for all fields). It doesn't disclose pagination, aggregation behavior, or potential performance implications (e.g., scanning large dataset). Since annotations already cover safety, a 2 acknowledges the description's added value but notes missing behavioral details.

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 front-loads the core purpose ('Get statistics on list/array field sizes') before giving examples. It earns its place by clarifying what 'field sizes' means (min/max/top) and examples of array fields. It could be slightly more concise by trimming 'in the ClinicalTrials.gov database' since the tool name already implies that, but the redundancy is minor.

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 simple interface (one optional param, no output schema, annotations indicating read-only and idempotent), the description covers the core semantics: what the tool computes and that it is useful for data distribution. However, it lacks details about the returned structure (e.g., in what format are the stats returned?), defaults for omitted 'fields' beyond what schema says (e.g., does it return all fields? how many?), and interaction with the sibling clinical_trials_size_stats. Since output schema is absent, the description should have explained return values more clearly. This is a moderate gap.

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's 'fields' parameter already has a description: 'Pipe-separated field names: 'Phase|Condition|InterventionName'. Omit for all.' This covers semantics fully (schema_description_coverage=100%). The tool description gives examples of fields and reinforces the purpose, but doesn't add meaning beyond the schema. Per the rubric, with full schema coverage, a 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 clearly identifies a specific verb ('Get statistics'), a resource ('list/array field sizes in the ClinicalTrials.gov database'), and names example fields (Condition, Intervention, Phase). It distinguishes itself from siblings like clinical_trials_field_values (which likely returns field values rather than size statistics) and clinical_trials_size_stats (which may also be related, though ambiguous). Differentiation from clinical_trials_size_stats is weaker because that sibling name could be synonymous with field sizes, so it doesn't fully distinguish from all siblings.

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 for understanding data distribution, but does not explicitly state when to use this tool versus alternatives. It does not mention any exclusions or alternatives like clinical_trials_size_stats or clinical_trials_field_values. The openWorldHint and readOnlyHint annotations give some sense of safe usage, but no direct guidance on when to prefer this tool. A clear context is provided ('for understanding data distribution'), but no 'use X instead' condition.

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 readOnly, idempotent, non-destructive, and open-world behavior. The description adds useful behavioral context by specifying the output type (top values, counts, distributions) and providing examples of concrete outputs, all consistent with annotations. No contradiction.

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 focused sentences with the main purpose front-loadedaint. The examples are concrete and the only minor fluff is the promotional phrase 'Powerful analytics tool', which does not detract significantly. Overall, every sentence 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?

For a simple read-only tool with two well-documented parameters and no output schema, the description is largely complete. The examples illustrate typical output patterns (counts by phase, top conditions). It does not explicitly describe the exact JSON response structure, but the provided context is sufficient for correct invocation in most cases.

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 documents both parameters fully. The description goes beyond the schema by giving illustrative examples for the 'fields' parameter (e.g., 'fields='Phase' shows trial count by phase'), which helps an agent understand the expected output shape. It does not mention the optional 'types' filter, but that is already well described in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Get value statistics') on a clear resource ('study data fields'), with concrete examples like 'fields='Phase' shows trial count by phase'. It clearly distinguishes this from search/detail tools, though it does not explicitly differentiate from closely named siblings like clinical_trials_field_sizes.

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 when to use the tool: when you need top values, counts, or distributions for trial fields. However, it provides no explicit alternatives or when-not-to-use guidance, leaving routing decisions to inference rather than direct instruction.

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 safety profile is covered. The description adds value by specifying that the tool returns schema-level information (field names, types, descriptions) rather than study records or statistics, giving the agent a clear expectation of the response nature.

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 with no filler. The first sentence states what the tool reveals, and the second states exactly when to use it. The front-loaded purpose makes it easy for an agent to quickly judge relevance.

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?

The tool is low-complexity: zero required parameters, two self-describing optional booleans, and no output schema. The description explains what the tool returns (field names, types, descriptions) and why an agent would call it. Nothing needed for correct selection or 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?

Schema description coverage is 100%: both boolean parameters are already documented with descriptive names and default values. The description adds no parameter-specific detail, but with full schema coverage that is acceptable; this is the baseline case where the schema carries the semantic weight.

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 ('Explore') and resource ('ClinicalTrials.gov study data model') and states the concrete outputs: field names, types, and descriptions. It distinguishes itself from data-returning siblings like clinical_trials_search and clinical_trials_detail by explicitly tying it to 'fields' parameter discovery and AREA[] filter syntax.

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 gives clear usage context: use it to discover fields for search/detail tools or to construct AREA[] filter expressions. It does not explicitly state when not to use it or name alternatives like clinical_trials_field_values or clinical_trials_enums, but the provided use cases are specific enough for an agent to route itself correctly.

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

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

Annotations already cover read-only/idempotent/non-destructive traits, and the description adds an availability constraint (`hasResults=true`) plus what data sections will be returned. It does not state the exact failure mode when the precondition is unmet, but the wording is enough to prevent incorrect invocation.

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, all substantive, with core purpose and eligibility front-loaded before return-content detail. There is no filler, repetition, or schema duplication.

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-parameter read-only tool with rich annotations, this captures purpose, input, expected return categories, and the precondition/route for finding valid trials. Although there is no output schema, the listed result sections give sufficient expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single `nct_id` parameter is already fully documented in the schema with format and example ('NCT00841061'), at 100% schema description coverage, so the description adds little semantic value beyond naming the lookup key. 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 verb and resource: 'Get posted results for a completed clinical trial by NCT ID.' It then enumerates the returned sections (outcome measures, adverse events, participant flow, baseline characteristics), which clearly separates this tool from sibling clinical_trials_detail and clinical_trials_stats.

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 states the precondition: 'Only works for trials where hasResults=true.' It also names the alternative for finding eligible trials: clinical_trials_search with agg_filters='results:with'. This gives the agent both a clear when-to-use boundary and the exact search path.

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, destructiveHint=false, idempotentHint=true, and openWorldHint=true, covering safety and non-mutating behavior. The description adds the return field list ('trial ID, title, status, phase, sponsor, conditions, enrollment, and hasResults flag') and hints at advanced filtering capabilities (Essie expressions, aggregation filters), which are behavioral details beyond the annotations. 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 moderately concise with five sentences. The first sentence clearly states the purpose and is front-loaded. The second lists return fields, and the next three provide targeted usage tips. Each sentence adds value; there is no filler or repetition. It is slightly long due to the multiple usage examples but remains efficient.

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?

The tool has 17 parameters and no output schema, yet the description covers the core search scope and return fields, and highlights advanced features (Essie, agg_filters). Pagination is not mentioned but is documented via page_token/page_size in the schema. The description does not explain sorting or combination of filters, but these are covered by schema documentation. Overall, it is reasonably complete for a search tool of this 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?

The schema covers 100% of parameters with descriptions, providing a baseline of 3. The description adds semantic guidance by mapping common search intents to specific parameters (e.g., 'condition', 'drug/intervention', 'sponsor') and gives usage examples for sponsor, filter_advanced, and agg_filters. This goes beyond the schema's field descriptions by clarifying when and how to use these parameters effectively.

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 action ('Search ClinicalTrials.gov for clinical trials') and enumerates the searchable dimensions (condition, drug/intervention, sponsor, status, phase, study type, location, title, free text). It clearly distinguishes from sibling tools like clinical_trials_detail or clinical_trials_stats by focusing on search and listing results, not on details or statistics.

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 concrete usage tips for specific parameters: 'Use sponsor filter to track pharma company research', 'Use filter_advanced for Essie expressions', 'Use agg_filters for shorthand filters'. These guide efficient use of the tool. However, it does not explicitly contrast with sibling search tools (e.g., 'for detailed trial info use clinical_trials_detail'), so the when-to-use vs alternatives 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds context about what the tool returns (total study count, average JSON size, size distribution, largest studies), which is useful but not rich. It doesn't contradict the annotations. The description doesn't disclose any performance characteristics, data freshness, or limitations (e.g., how 'size' is measured or whether results are cached). With the safety profile covered by annotations, a 3 is appropriate—the description adds some value but not deep behavioral context.

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 with no filler. The first sentence front-loads the concrete deliverables (count, average size, size distribution, largest studies), and the second adds a quick contextual framing about scope and data volume. The 'quick overview' phrase in the second sentence is slightly redundant with the first sentence's enumeration but reinforces the tool's lightweight nature. No wasted words overall, though the second sentence could arguably be trimmed.

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 tool with no output schema, the description carries the burden of explaining what the tool returns, which it does reasonably well by enumerating the four outputs. The main gap is the failure to differentiate from the sibling 'clinical_trials_stats' and the absence of any note about data freshness or update frequency, which matters for a database-statistics tool. Given the tool's simplicity, the description is mostly adequate but leaves the sibling-ambiguity question unresolved, which an agent would need to resolve on its own.

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, making schema coverage trivially 100%. With no parameters to document, the baseline is 4, and the description appropriately focuses on describing the tool's outputs rather than parameter syntax. The enumeration of what the tool returns (count, average size, distribution, largest studies) substitutes for parameter documentation and helps the agent understand the result shape. Nothing is missing in terms of parameter semantics since there are no inputs to clarify.

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 with a specific verb ('Get') and resource ('database statistics'), enumerating concrete outputs: total study count, average study JSON size, size distribution, and largest studies. The first sentence is informative and specific. However, it fails to differentiate this tool from the nearly identical sibling 'clinical_trials_stats', which likely serves a similar statistical purpose. The 'size' focus is evident in the name but not explicitly highlighted in the description to distinguish it.

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 offers minimal usage context, noting it provides a 'quick overview of the ClinicalTrials.gov database scope and data volume.' This implies when to use it (for database-level overviews) but provides no explicit when-to-use vs when-not-to-use guidance and no exclusions. Critically, it never mentions or contrasts the very similar sibling 'clinical_trials_stats', leaving an agent to guess which statistical tool to invoke for a given task. For a tool with such a close sibling, the absence of routing guidance is a significant gap.

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 idempotentHint=true, so safety is covered. The description adds meaningful behavioral context beyond annotations: it 'queries 8 statuses in parallel for comprehensive breakdown,' which implies parallel calls and potentially higher latency or rate-limit impact. It also clarifies the nature of the output (counts by status, not a trial list). 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 four short, focused sentences. The main purpose is front-loaded, followed by output format, accepted inputs with examples, and a behavioral note. Every sentence earns its place with 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?

For a simple 2-parameter tool with no output schema, the description sufficiently explains what the tool returns (counts by status) and how it handles both condition and drug inputs. It does not detail the exact response structure or status list beyond 'etc.', but the general shape is clear. Annotations cover safety, so the description is nearly 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 description coverage is 100% with both parameters already documented. The description adds example values ('breast cancer', 'semaglutide') and clarifies that condition can be a drug/intervention, but this mostly repeats schema guidance. It does not add significant meaning beyond the schema, so 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 states a specific verb+resource: 'Get trial count breakdown by recruitment status for a condition or drug/intervention.' It clearly differentiates from sibling tools like clinical_trials_search and clinical_trials_detail by focusing on counts by status rather than searching or detailing individual trials. The examples of diseases and drug names further clarify the scope.

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 when to use the tool (when a count breakdown by status is needed) and clarifies that it accepts both diseases and drug names. However, it does not explicitly mention alternatives or provide when-not-to-use guidance relative to siblings like clinical_trials_search or clinical_trials_by_location. The usage context is clear but not explicitly routed.

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, so the safety profile is covered. The description adds the data categories but doesn't disclose behavioral traits like pagination, rate limits, or what happens with no filters. It provides some context beyond annotations but not rich behavioral 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 a single, well-structured sentence. It front-loads the purpose ('Query CMS hospital data'), then lists the data categories and filters without any redundant or vague 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?

The description covers the core purpose and filter options but doesn't mention the default dataset (hospital_info) or the default limit (50), which are in the schema. It also doesn't describe the response format, though there is no output schema. For a query tool with optional parameters, this is adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.