Server Quality Checklist

Tool Scores

• check_brokerA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description fully carries the behavioral disclosure burden. It discloses the paid nature ($0.05, x402 USDC on Base), states it's a live lookup, mentions automatic payment handling, and details return fields including a provenance URL. This exceeds typical transparency, though it omits potential failure modes or rate limits.

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

  Conciseness4/5

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

  The description is a single paragraph, front-loaded with the core purpose and cost, then expanding to return fields and use cases. Every sentence contributes value, though it is longer than strictly necessary and includes marketing-like phrasing ('natural companion') that could be trimmed.

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

  Completeness4/5

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

  Given the tool's simplicity (1 param, no output schema, no annotations), the description is fairly complete. It covers purpose, cost, source, return data, verification URL, and use cases. Missing details include query input format and any error/empty-result behavior, but the description is solid for a lookup tool.

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

  Parameters3/5

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

  The schema has one parameter (query) with 0% description coverage, so the description must compensate. It implies query is the subject (a stockbroker, adviser, or firm) but does not explicitly state the expected input format (e.g., name or CRD number). The description adds some meaning but stops short of fully clarifying the parameter syntax.

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

  Purpose5/5

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

  The description clearly states the tool's function: 'Check a stockbroker, investment adviser, or brokerage firm for disciplinary history.' It specifies the resource (FINRA BrokerCheck registry) and scope (disciplinary history), and distinguishes itself from siblings like screen_entity_free by emphasizing the paid, registry-specific nature.

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

  Usage Guidelines4/5

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

  The description explicitly lists use cases: 'For KYC, AML, counterparty due diligence, adviser vetting, and investment fraud checks; the natural companion to the 11 authority sanctions screen.' This provides clear context for when to use the tool, though it does not explicitly name alternatives or state when not to use it.

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

• get_catalogA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of disclosure. It explicitly states the tool is FREE, enumerates returned fields, mentions the provenance URL for every record, and outlines the micropayment flow via get_record. It does not cover pagination behavior or potential rate limits, but the core behavioral context is well covered.

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

  Conciseness4/5

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

  The description leads with the core purpose and return values, then the extensive enumeration of covered data verticals is contextually useful for a catalog tool. While lengthy, the content is relevant and not redundant with the schema or annotations.

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

  Completeness4/5

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

  Given the tool's complexity and the presence of an output schema, the description sufficiently covers the catalog's scope, filtering options, and the next-step purchasing workflow. The main gap is the lack of detail for `limit`, `offset`, and `record_key`, but the overall context is strong enough for an agent to use the tool effectively.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must compensate. It does explain `source` with concrete examples and `data_type` as a substring, but it omits any explanation of `limit`, `offset`, and `record_key`, which leaves key parameters underspecified.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: 'Browse the OSF catalog (FREE)' and specifically lists what it returns (record_ids, prices, data types, provenance URLs). This distinguishes get_catalog from sibling tools like get_record (purchase) and specialized search_* tools.

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

  Usage Guidelines4/5

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

  The description provides clear usage context: use get_catalog to browse and select records, then 'Call get_record with a record_id to purchase the full record'. It also explains optional filters, but it does not explicitly mention when not to use this tool vs. the specialized search siblings.

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

• search_economic_indicatorsA
  4.2/5.0
  Behavior4/5

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

  Description discloses key behavioral traits: it is free, requires no API key, searches many named sources, and returns specific metadata fields per match. It also notes that the full record requires purchasing via get_record. Given no annotations exist, this provides substantial transparency beyond the bare operation, though it doesn't mention rate limits or error handling.

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

  Conciseness4/5

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

  The description is moderately long but each sentence provides useful information: access, purpose, sources, return fields, and usage context. The Args section is clearly separated, but the 'FREE' note could be positioned later to front-load the core function.

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

  Completeness5/5

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

  Given the tool has a single simple parameter and no output schema, the description covers the return values explicitly and explains how to follow up with get_record. It also lists the broad scope of sources, making it sufficiently 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.

  Parameters3/5

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

  The only parameter, query, is described as 'keyword(s) to search', which is minimal but the main description clarifies that it relates to economic measures. With 0% schema coverage, the description compensates with some context but lacks examples or query formatting guidance.

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

  Purpose5/5

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

  The description clearly states the tool's function: it answers what the official series for an economic measure is and where it comes from. It lists multiple authoritative data sources and specifies the return fields, distinguishing it from sibling search tools for other domains.

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

  Usage Guidelines4/5

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

  Provides context for when to use: macro research, model inputs, and grounding answers in citable official series. It also directs users to call get_record with a record_id for the full series, indicating an alternative/follow-up tool. However, it doesn't explicitly state when not to use this tool versus other search tools.

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

• search_regulations_lawA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description fully carries the transparency burden. It discloses pricing ('FREE, no payment and no key'), output fields (title, agency, date, provenance URL, record_id), and the paywall model (call get_record to buy the full document). This is substantial context beyond a typical tool description.

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

  Conciseness4/5

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

  The description is longer than two sentences but every sentence adds distinct value: pricing, sources, output, paywall, use cases, and sibling distinction. Slight redundancy ('FREE' and 'no payment and no key') but overall efficient and front-loaded.

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

  Completeness4/5

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

  For a broad search tool with vague schema and no output schema, the description is remarkably complete: it explains what is searched, what is returned, how to access full documents, and when to use alternatives. Minor gaps exist (e.g., pagination or sorting) but they are not crucial for initial selection.

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

  Parameters2/5

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

  The schema has only one parameter 'query' with zero description coverage. The description adds 'keyword(s) to search,' which is minimal and not enough to clarify query syntax, boolean operators, or how the query is applied across the multiple sources. Given the low schema coverage, the description should compensate more than it does.

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

  Purpose5/5

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

  The description clearly states the tool searches US federal regulations and sources like eCFR, Federal Register, Congress.gov, Regulations.gov, and GovInfo. It specifies a focused question ('what does US federal regulation say about this, and what is being changed') and explicitly distinguishes from search_legal_cases, ensuring no confusion with sibling tools.

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

  Usage Guidelines5/5

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

  Explicit use cases are provided: 'For regulatory compliance, policy monitoring, and rulemaking research.' Also gives an alternative: 'Court opinions are a separate tool: call search_legal_cases for case law,' which tells the agent when NOT to use this tool and where to go instead.

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

• is_cve_exploitedA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly mentions the paid status ($0.05 USDC on Base), the automatic x402 payment handshake, and the response structure with provenance URLs. This is strong bonus context beyond a typical read-only query. It does not cover error handling or invalid CVE behavior, which 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.

  Conciseness4/5

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

  The description is moderately long but every sentence contributes: payment details, input format, output types, provenance URLs, use cases, and payment handshake. There is no fluff, though it could be tightened slightly by moving the use-case sentence earlier or merging some clauses. It remains well-structured and front-loaded.

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

  Completeness4/5

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

  For a one-parameter tool with no output schema, the description covers the key aspects: what the tool does, what it returns, why you might use it, and the payment requirement. Edge cases (e.g., nonexistent CVE, API errors) are not addressed, but given the simplicity and the richness of the provided details, the description is sufficiently complete.

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

  Parameters4/5

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

  The schema only defines cve_id as a required string with no description (0% coverage). The description compensates by giving the required format via example: 'Pass a CVE id (e.g. CVE-2026-33017).' This is essential for correct invocation. It could add more detail (e.g., case sensitivity, whitelist of formats), but the example is sufficient.

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

  Purpose5/5

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

  The description clearly states the tool's function: 'Check whether a specific CVE is being actively exploited in the wild.' It enumerates specific outputs (KEV catalog status, EPSS score, CVSS severity, provenance URLs) and gives a concrete example input (CVE-2026-33017). This distinguishes it from sibling search tools, which are broader searches rather than direct lookups.

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

  Usage Guidelines4/5

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

  The description provides clear usage context by listing relevant workflows: 'vulnerability management, patch prioritization, threat intelligence, and DevSecOps agent workflows.' It also highlights the paid nature, which informs cost-sensitive decisions. However, it does not explicitly name alternatives or state when not to use the tool, so it stops 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.

• search_consumer_protectionA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of disclosing behavior. It states it is free, requires no key, returns specific fields (title, agency, dates, URL, record_id), and that full records require purchase via get_record. It also notes the historical coverage since 2004. It does not mention pagination or error handling, but for a search tool this is reasonable.

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

  Conciseness5/5

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

  The description is front-loaded with the key value proposition ('FREE, no payment and no key'), then states purpose, data sources, return fields, alternative tool, and use cases. Every sentence adds useful information and the structure is logical and efficient.

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

  Completeness4/5

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

  Given the tool's complexity (multiple data sources, historical data, different access levels), the description covers the essential aspects: what it searches, returns, costs, and when to use. It lacks details on result limit/sorting, but these are not critical for the stated use cases.

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

  Parameters4/5

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

  The schema has a single 'query' property with no description (0% coverage). The description compensates by defining 'query' as 'keyword(s) to search.' This is sufficient for the simple parameter, though it does not elaborate on query syntax or constraints.

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

  Purpose5/5

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

  The description clearly states what the tool does: 'Answers has this product, drug, device or vehicle been recalled, and what have consumers complained about' and specifies the exact data sources (CFPB, NHTSA, CPSC, FDA). It distinguishes from siblings like search_gov_spending by focusing on consumer protection and recalls.

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

  Usage Guidelines4/5

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

  It provides explicit context for when to use the tool ('For product safety review, supplier screening, and recall monitoring') and names an alternative (get_record for full records). It does not explicitly state when not to use it, but the guidance is clear enough for an agent to differentiate.

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

• search_sec_filingsA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It discloses the free/no-key nature, lists return fields (filer/company, form type, filing date, provenance URL, record_id), and explains the free search vs. paid full-filing model. This is good behavioral disclosure for a read-only search tool.

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

  Conciseness5/5

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

  The description is appropriately sized, front-loads the key value proposition (FREE, no key, search SEC filings), and every sentence adds useful information. No redundant text.

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

  Completeness4/5

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

  For a one-parameter search tool with no output schema, the description covers purpose, usage, return fields, and pricing. It lacks mention of result limits or pagination, but these are minor gaps for a simple search tool.

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

  Parameters4/5

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

  Schema coverage is 0%, but the Args section explains the query parameter with an example ('Berkshire 13F'). This compensates for the schema gap, though it does not cover advanced query syntax or result limiting.

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

  Purpose5/5

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

  The description clearly states the tool searches US SEC filings, listing specific form types (13F, Form 4, 8-K, 10-K, XBRL, EDGAR full text, litigation releases, administrative proceedings). This specific verb+resource distinguishes it from sibling search tools covering other domains.

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

  Usage Guidelines4/5

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

  Provides clear use cases: 'financial research, insider activity monitoring, and issuer due diligence.' Also directs users to call get_record with a record_id to purchase the full filing. Does not explicitly exclude alternative tools, but the context is sufficiently clear.

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

• get_recordA
  4.5/5.0
  Behavior5/5

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

  With no annotations, the description carries full burden and does so admirably: it discloses the cost (x402 USDC on Base), automatic payment handshake, and the provenance-block return, giving the agent critical 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.

  Conciseness3/5

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

  The description is clear but includes a long list of OSF verticals that, while informative, is not essential for tool selection and adds wordiness. The core guidance is front-loaded, but the extra list makes it less concise than ideal.

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

  Completeness5/5

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

  Despite having no output schema, the description fully covers what the tool returns (full record plus provenance), how to obtain the required parameter (via get_catalog), and the payment process. For a single-parameter tool, this is complete.

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

  Parameters4/5

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

  Schema only defines record_id as an integer with no description. The description compensates by explaining that record_ids come from get_catalog and that they reference specific OSF records, adding practical guidance beyond the schema.

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

  Purpose5/5

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

  The description clearly states the specific action: purchase and retrieve one verified OSF record by record_id, and highlights the unique paid/provenance aspect that distinguishes it from search and catalog sibling tools.

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

  Usage Guidelines4/5

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

  It explicitly instructs to browse get_catalog first (free) to find record_ids and prices, implying this tool should be used after catalog lookup. It does not explicitly list alternative tools for free retrieval, but the paid vs free distinction is clear.

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

• search_aircraft_registryA
  4.5/5.0
  Behavior4/5

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

  Despite lacking annotations, the description discloses free/no key access, returns partial data (record_id) with full registration requiring payment, and mentions a coverage block indicating data completeness. This gives the agent a solid understanding of 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.

  Conciseness4/5

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

  The description is moderately long but well-structured with a clear intro, return field list, note about get_record, use cases, and args section. Every sentence provides value, with no filler.

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

  Completeness5/5

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

  Covers query usage, return fields, coverage block, and the follow-up get_record tool. With no output schema and a single parameter, the description provides all necessary context for effective invocation.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the description fully compensates with an elaborate 'Args:' section explaining the query parameter with concrete examples like 'Cessna 172', 'N17973', and 'MARION TX', as well as listing searchable fields.

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

  Purpose5/5

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

  Description clearly states it searches US civil aircraft registrations from the FAA Releasable Aircraft Database, listing many searchable fields and return fields. Resource and scope are unambiguous, distinguishing it from sibling search tools.

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

  Usage Guidelines4/5

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

  Provides explicit use cases (aircraft ownership lookup, fleet research, asset tracing, due diligence) and instructs to call get_record to buy full registration, showing how to proceed beyond the free search. Lacks explicit when-not-to-use compared to other search tools, but the domain differentiation is clear.

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

• search_environmental_dataA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses the free/no-key access, what is returned (record title, agency, dates, provenance URL, record_id), and that full records require a separate paid call. This goes beyond a minimal listing and helps the agent set expectations, though it could mention pagination or error behavior.

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

  Conciseness5/5

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

  The description is front-loaded with the most important fact ('FREE, no payment and no key'), then clearly lists data sources, return fields, and billing guidance. Every sentence adds useful information without fluff. The Args section is minimal and necessary.

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

  Completeness5/5

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

  Given the tool's scope, the description is remarkably complete. It names all major data sources, lists the exact return fields, notes the free/buy model, and provides example workflows. With no output schema, this description alone gives the agent a strong understanding of what to expect.

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

  Parameters4/5

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

  The schema only defines 'query' as a string with no description. The description adds the semantic 'keyword(s) to search', which clarifies the parameter's purpose. For a single, simple parameter this is adequate compensation for low schema coverage.

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

  Purpose5/5

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

  The description uses a specific verb ('searches') and names the exact resources: USGS earthquakes and water data, NOAA weather, alerts and tides, FEMA disaster declarations, EPA compliance, and GBIF records. It clearly distinguishes this tool from sibling search tools by enumerating the data sources.

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

  Usage Guidelines4/5

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

  The description provides clear context: it answers a specific type of question and lists target workflows ('site and facility diligence, climate and hazard exposure checks, and disaster response workflows'). It also names an alternative, 'call get_record with a record_id to buy the full record', which is useful. It does not explicitly say when not to use it, but the use cases are clear.

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

• search_gov_spendingA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. It discloses that the tool is 'FREE, no payment and no key,' includes access context, and explains the return fields (recipient, agency, amount, dates, NAICS, provenance URL, record_id). It also implies a read-only search behavior and its role as a precursor to paid records, though it does not mention rate limits or pagination explicitly.

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

  Conciseness4/5

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

  The description is well-structured, front-loaded with the free/nokey access note and followed by the tool's purpose, return values, usage guidance, and argument details. Every sentence contributes useful information without redundant wording, though it is slightly longer than the minimum needed.

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

  Completeness4/5

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

  With only one parameter, no output schema, and no annotations, the description covers essential aspects: what the tool searches, what it returns (a list of fields), how to use it (query), and the relationship to get_record. It does not detail the exact response structure or edge cases, but it is sufficient for an agent to select and invoke the tool correctly.

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

  Parameters4/5

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

  The schema only provides the property name and type with no description, but the description's 'Args:' section adds meaning: 'query: keyword(s) to search, e.g. "navy radar".' This clarifies the parameter's purpose and provides an example, adding significant value beyond the schema.

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

  Purpose5/5

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

  The description clearly states the tool's verb and resource: 'Search US federal spending' across specific sources (USAspending, SAM.gov, Grants.gov). It distinguishes itself from sibling search tools by naming the exact domain and data sources, making it unambiguous which tool to select for federal spending searches.

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

  Usage Guidelines5/5

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

  Explicitly provides when to use and an alternative: 'Use this to find out whether OSF holds what you need before spending anything, then call get_record with a record_id to buy the full record.' It also lists concrete use cases like govcon market intelligence and vendor due diligence, giving clear context for selection.

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

• lookup_entityA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full disclosure burden. It transparently covers the paid nature ($0.05, x402 USDC), payment handshake, registry sources, match behavior (exact vs candidate), and return fields (legal name, status, type, jurisdiction, identifiers, provenance URL). It could add edge-case behavior (e.g., not-found responses), but the core transactional and lookup behavior is well disclosed.

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

  Conciseness5/5

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

  The description is dense but every sentence adds essential value: payment, registries, query modes, output fields, use cases, and payment handshake. It is front-loaded with the most critical operational detail (paid) and avoids redundant phrasing.

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

  Completeness5/5

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

  For a paid, multi-registry lookup tool with a single unannotated parameter and no output schema, this description is remarkably complete. It explains what the tool does, how to invoke it, what it returns, when to use it, and how payment works — covering all information an agent needs to select and call it correctly.

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

  Parameters5/5

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

  The schema has one opaque 'query' parameter with 0% description coverage. The description fully compensates by specifying accepted values: NPI, LEI, FDIC cert, CIK, EIN for exact matches, or a name for candidate matches. This leaves no ambiguity about how to populate the parameter.

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

  Purpose5/5

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

  The description uses a specific verb ('Verify') and names the resource ('entity / counterparty by identifier or name'), then goes further by enumerating the authoritative registries (NPI, LEI, FDIC, CIK, EIN). This clearly differentiates it from sibling search and screening tools, which focus on broader queries rather than exact registry-backed verification.

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

  Usage Guidelines4/5

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

  Provides explicit instructions on how to query ('Pass an identifier ... or a name') and lists concrete use cases such as KYC, KYB, and counterparty due diligence. It does not explicitly mention exclusions or alternatives to sibling tools like screen_entity, but the context is clear enough for appropriate tool selection.

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

• search_healthcareA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries full burden. It discloses that the tool is free with no key, searches multiple specific sources, returns title, identifiers, provenance URL, and record_id, and that full records require payment. It does not mention rate limits, result limits, or error conditions, but provides substantial behavioral context beyond what annotations would typically offer.

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

  Conciseness4/5

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

  The description is information-dense and logically organized, covering availability, sources, return fields, payment model, use cases, and alternatives. It is slightly longer than necessary with minor redundancy ('Free to search' repeats the opening) but every major aspect earns its place.

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

  Completeness4/5

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

  For a single-parameter search tool with no output schema, the description adequately explains what is searched, what is returned, and how the free vs paid model works. It does not specify pagination, sorting, or result count limits, but these are not critical for basic usage and the description otherwise feels complete.

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

  Parameters5/5

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

  The schema has only a 'query' field with no description, but the tool description's Args section explains 'query: keyword(s) to search, e.g. a provider name or NPI, drug name, condition, or NCT id.' This fully compensates for the schema's lack of parameter documentation.

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

  Purpose5/5

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

  The description explicitly states it searches healthcare registries including CMS NPPES, RxNorm, ClinicalTrials.gov, and FDA recalls, and returns matching records. It distinguishes itself from sibling lookup_entity and get_record by clarifying the search use case and the paywall for full records.

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

  Usage Guidelines5/5

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

  It clearly states suitable use cases: 'For provider verification, prescriber vetting, trial status checks, and drug safety review.' It also directs to alternatives: 'To verify a provider by identifier rather than search for one, call lookup_entity' and 'call get_record with a record_id to buy the full record.' This explicitly covers when to use this tool versus siblings.

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

• search_cyber_threatsA
  4.7/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool is free and requires no key, returns specific fields (id, title, severity/score, URL, record_id), and that full records cost money via get_record. While it omits potential rate limits or pagination, the transparency is strong for a search tool.

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

  Conciseness5/5

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

  The description is long but every sentence adds value. It is front-loaded with the key benefit ('FREE, no payment and no key'), then lists data sources, return fields, and monetization details in a logically ordered way. The Args section is clearly separated, and no information is redundant.

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

  Completeness5/5

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

  Given the tool's complexity (multiple data sources, partial free results, paid full records), the description covers search scope, output format, cost model, and the alternative tool. The absence of an output schema is mitigated by explicitly listing the return fields, making the description sufficient for an agent to understand expected results.

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

  Parameters4/5

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

  The only parameter, query, is explicitly documented with a description ('keyword(s) to search') and a concrete example ('Microsoft Exchange'). This compensates for the 0% schema description coverage, giving an agent enough semantics to construct a valid query.

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

  Purpose5/5

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

  The description clearly states a specific verb ('Search') and resource ('cybersecurity intelligence') and enumerates the exact data sources covered (CVE, EPSS, CISA KEV, advisories, CWE, ATT&CK). It also distinguishes itself from the sibling tool is_cve_exploited by specifying when that alternative is more appropriate, making it easy for an agent to select the correct tool.

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

  Usage Guidelines5/5

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

  Provides explicit usage context: it is free to search, full records require a separate call to get_record, and is_cve_exploited is the better choice when only checking active exploitation of a known CVE ID. This offers clear when-to-use and when-not-to-use guidance compared to alternatives.

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

• search_legal_casesA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden and does well. It discloses that the service is free and requires no API key, specifies the data source (CourtListener), lists what fields are returned, and explains the purchase mechanism via get_record. Minor gaps like rate limits or pagination are not mentioned, but the description still offers substantial transparency.

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

  Conciseness5/5

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

  The description is concise and well-structured. It starts with the key benefit (FREE, no key), explains the scope, lists return fields, and then provides usage examples in the Args section. There is no redundant information, and each sentence adds value.

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

  Completeness5/5

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

  Given the simple input (one query string) and lack of an output schema or annotations, the description is remarkably complete. It covers the tool's purpose, data scope, return fields, cost implications, and a clear path to obtain fuller results. An agent can confidently decide when and how to invoke this tool.

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

  Parameters4/5

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

  Although the input schema only shows a required 'query' string, the description elaborates with examples ('"miranda arizona"' or '"ninth circuit qualified immunity"') and clarifies that it accepts keyword(s). This adds meaning beyond the schema. It doesn't cover advanced query syntax, but for a single free-text parameter, this is sufficient.

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

  Purpose5/5

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

  The description opens with a specific verb ('Search') and clearly defines the resource: 1.55 million+ US federal court opinions, including SCOTUS and appellate circuits, plus SEC litigation releases. It explicitly distinguishes itself from a sibling tool by noting that search_regulations_law covers regulations, statutes, and the Federal Register, thus clarifying its own scope.

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

  Usage Guidelines5/5

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

  The description states clear use cases: 'For precedent checks, citation lookup, and enforcement history.' It also provides an explicit exclusion: regulations and statutes are handled by search_regulations_law. Additionally, it directs users to call get_record for full opinions, which helps in selecting the appropriate tool in the workflow.

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

• search_patentsA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It discloses 'FREE, no payment and no key', the domain of search (US granted patents), and the free-to-search vs. paid full-record model. It does not mention result limits or pagination, so 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.

  Conciseness5/5

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

  The description is concise and front-loaded with key information (FREE, no key), then quickly covers search scope, returned fields, and usage. The Args section is helpful without being verbose.

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

  Completeness4/5

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

  For a single-parameter tool with no output schema, the description explains the query, return fields, and downstream action (get_record). It lacks pagination/result-limit details but is otherwise complete for a search tool.

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

  Parameters5/5

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

  The single parameter 'query' is thoroughly explained with examples ('lithium battery cathode', 'Panasonic', patent number), adding significant meaning beyond the bare schema. Schema coverage is 0%, so this is fully compensated.

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

  Purpose5/5

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

  The description clearly states it 'Search granted US patents from the USPTO Open Data Portal' with specific search criteria (title, assignee, inventor, patent number, technology area) and lists return fields. This differentiates it from sibling search tools by being patent-specific.

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

  Usage Guidelines5/5

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

  Explicitly mentions use cases ('prior art checks, freedom to operate research, competitor IP monitoring, and patent portfolio lookup') and names get_record as the alternative for buying full records, giving clear when-to-use and alternative guidance.

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

• search_research_papersA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral transparency. It discloses the cost model (free search, paid records), that no key is required, and the exact return fields (title, authors, venue, year, DOI, provenance URL, record_id). However, it does not mention pagination, rate limits, or result count limits, which are typical search tool behaviors. Overall, it is quite transparent but not exhaustive.

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

  Conciseness5/5

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

  The description is efficiently organized: cost info first, then scope, then returns, then workflow guidance, then use cases, and finally the args section. Every sentence adds value, and the structure is front-loaded with the most critical information. It is reasonably concise given the amount of helpful context packed in.

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

  Completeness4/5

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

  The description covers the tool's purpose, scope, return format, cost model, and how it connects with get_record. Since there is no output schema, the description's listing of return fields is essential and well done. However, missing details like result limits, pagination, or sorting leave minor gaps for a search tool. Overall, it is sufficiently complete for an agent to decide when and how to use it.

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

  Parameters5/5

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

  The schema provides only the parameter name 'query' with no description (0% coverage). The description compensates fully by explaining that query is 'keyword(s) to search' and giving a concrete example ('CRISPR off-target'). This makes the parameter's meaning and usage clear, exceeding what the schema alone offers.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: search scholarly works across multiple databases. It specifies the verb (search), the resource (1.2M+ scholarly works), and the scope (specific sources). It also distinguishes itself from siblings by mentioning the companion get_record tool for buying full records, making its role in the workflow explicit.

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

  Usage Guidelines5/5

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

  The description explicitly explains when to use this tool: 'Free to search, so probe coverage before you spend; call get_record with a record_id to buy the full record.' It also lists relevant use cases (literature review, citation checking, research agent workflows). This provides clear guidance relative to get_record and other potential search tools in the sibling set.

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

• sample_recordA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses the key behavior: it is a paid operation ($0.001, x402 USDC on Base), returns the full record plus provenance, and payment is automated via x402 handshake. It also notes that the record is 'verified,' adding context about data quality. This is substantial for a read-like tool.

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

  Conciseness5/5

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

  Four sentences, each carrying distinct information: cost/operation, return value, use case, and prerequisite. The most critical detail (cost and paid nature) is front-loaded. No fluff or repetition; every sentence earns its place.

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

  Completeness5/5

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

  For a single-parameter tool with no output schema, the description covers purpose, cost, payment mechanism, return contents (full record + provenance), and relationship to free browsing. It gives an agent enough to invoke correctly and understand the financial implications.

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

  Parameters4/5

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

  The only parameter, record_id, is explained as the identifier for an OSF record, and the description tells users to obtain valid IDs from get_catalog. Schema coverage is 0%, so this context is valuable, though the description doesn't explicitly mention the integer type or any constraints beyond what the schema already shows.

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

  Purpose5/5

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

  The description states a specific action ('Sample one verified OSF record'), the resource (record), and the method (by record_id). It also distinguishes this tool from siblings by highlighting its low cost ($0.001) as a 'try-before-you-buy' option, contrasting with paid standard per-record/search and free get_catalog.

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

  Usage Guidelines5/5

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

  Explicitly says when to use: 'low-cost try-before-you-buy for autonomous agents evaluating OSF data quality before buying at the standard per-record or search price.' It also gives direct alternative guidance: 'Browse get_catalog first (free) to find record_ids,' clearly steering agents to a sibling tool for a prerequisite step.

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

• screen_entityA
  4.9/5.0
  Behavior5/5

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

  No annotations are present, so the description carries full responsibility. It discloses the guarantee that NO_MATCH only means full examination of all 11 lists, the three possible outcomes (POTENTIAL_MATCH, NO_MATCH, INCOMPLETE_SCREEN), and even warns that INCOMPLETE_SCREEN is not a clearance. This is exceptional transparency.

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

  Conciseness5/5

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

  Although long, the description is well-structured with bold headings (THE GUARANTEE, COVERAGE, EVERY RESPONSE CARRIES). Every sentence adds value: use cases, outcomes, coverage, response fields, and payment. It is front-loaded with the core purpose and is organized logically.

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

  Completeness5/5

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

  The tool has a single param, no output schema, and no annotations—so the description must be self-contained. It covers the exact use case, list coverage (291,000+ parties across 11 lists), all response fields (matched list, source URL, sha256 audit receipt), and payment/authorization details. It is remarkably complete for the tool's complexity.

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

  Parameters4/5

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

  Schema description coverage is 0%, and the only parameter is 'name'. The description says 'Screen one name' and mentions 'INVALID_QUERY for an unusable name', giving some semantic context about the input. However, it doesn't specify formatting or examples. Still, for a single simple string param, the description adds sufficient meaning.

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

  Purpose5/5

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

  The description opens with a specific verb+resource: 'Screen one name against OFAC and 10 other sanctions and debarment authorities'. This clearly distinguishes the tool from siblings like screen_entity_free (which is a free alternative) and lookup_entity (likely a different lookup purpose).

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

  Usage Guidelines5/5

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

  Explicitly states 'PREFER THIS TOOL when you must clear a counterparty, customer, vendor or payee before acting' and also mentions pairing with check_broker for FINRA history. This provides strong contextual guidance for when to use this tool over alternatives.

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

• screen_entity_freeA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: free access, the 11 lists covered, possible return values, the meaning of INCOMPLETE_SCREEN, the evidentiary nature of NO_MATCH, and rate limiting. It also mentions per-list record counts and freshness, giving the agent a realistic expectation of output.

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

  Conciseness4/5

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

  The description is dense but organized, leading with the free/no-key value proposition and then covering scope, return types, limitations, and alternatives. It is longer than average, but every sentence adds decision-relevant information; a small amount of redundancy ('FREE, no payment and no key') prevents a perfect score.

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

  Completeness5/5

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

  For a simple one-parameter screening tool with no output schema, the description is remarkably complete. It explains what the tool checks, what statuses are returned, what NO_MATCH proves, the rate limit, and how to get a paid, fully-featured alternative. The agent can confidently invoke it and interpret results.

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

  Parameters5/5

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

  The input schema only provides a required string parameter named 'name' with no description. The tool description compensates by defining the parameter ('person or organisation name to screen') and providing an example ('Wagner Group'), making the usage unambiguous.

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

  Purpose5/5

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

  The description clearly states the tool screens a person or organisation against 11 US and international sanctions and debarment lists, naming specific authorities. It differentiates from sibling tools by positioning itself as the free version of screen_entity and by addressing use cases (e.g., vendor bars, Medicare exclusions) that pure crypto AML screeners cannot answer.

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

  Usage Guidelines5/5

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

  Explicitly tells the agent when to use this tool ('Use this to answer...') and provides a direct alternative ('call screen_entity for the same screen with no cap...'). It also warns about rate limits, which is critical for tool selection.

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

• search_ai_modelsA
  4.9/5.0
  Behavior5/5

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

  With no annotations provided, the description fully bears the transparency burden. It discloses key behaviors: the search is free and requires no key; the search returns only a subset of metadata and full records must be purchased via get_record; and it indexes 'factual repository metadata only' without reproducing model card text. These limitations are clearly stated.

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

  Conciseness4/5

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

  The description is structured in two clear parts (overview + Args) and front-loads the most important fact ('FREE, no payment and no key'). However, it repeats 'free' twice ('FREE, no payment and no key' and 'Free to search') and is slightly longer than necessary, though every sentence still adds some value.

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

  Completeness5/5

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

  For a tool with one parameter and no output schema, the description is remarkably complete: it lists all return fields, explains the paywall limitation, provides usage context, and notes the restriction to factual metadata. It even mentions the relationship to get_record, making the overall workflow clear.

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

  Parameters5/5

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

  The only parameter, `query`, is given a plain type in the schema but the description adds meaningful semantics: 'keyword(s) to search' and examples such as 'image segmentation', 'nvidia', or 'apache-2.0'. This goes beyond the basic schema and helps the agent formulate valid queries.

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

  Purpose5/5

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

  The description uses a specific verb ('Search') and clearly identifies the resource ('AI and machine learning models on the Hugging Face Hub') along with search dimensions ('by name, author or organization, task, library, or license'). It also distinguishes itself from sibling search tools by naming its domain and enumerating the exact fields returned.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use this tool: 'For model selection, license screening before adoption, and dependency review.' It also clearly directs users to an alternative tool: 'call get_record with a record_id to buy the full metadata record,' providing a when-to-use vs. when-to-move-on contrast.

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