Govparse Government Data Gateway

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

With no annotations provided, the description carries the behavioral disclosure burden. It transparently lists what the tool returns (signals/legs, plain-English restatement, narrative, fit score, expected rate, free sample) and states it is a 'FREE preview', conveying the preview nature. It does not detail limitations like the deterministic selection rule, but the schema description covers that. No contradictions with annotations (none provided).

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 purpose and enumerates return values, the second highlights the free-preview relationship to get_leads. It is front-loaded with the primary action and zero filler. Every sentence adds meaningful 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?

Given the tool's complexity (8 params, nested objects, no output schema), the description lists return values but not their structure. However, the schema description is extremely rich and supplies the selection logic, making the combined context sufficient for an agent to invoke correctly. The description clearly frames the tool's role relative to get_leads, which is essential context for a preview 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?

The input schema has 100% parameter coverage with detailed descriptions, including the nested 'parse' object, enums, and the role of 'query'. The tool description adds only a high-level paraphrase ('what you sell and who you target') without new parameter-specific details. Since schema coverage is complete, the baseline of 3 is appropriate, though the description does reinforce the intended user-facing intent.

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 'Compose' and the resource 'lead-generation Parse', specifying it transforms 'what you sell and who you target'. It explicitly distinguishes itself from the paid sibling 'get_leads' by calling itself the 'FREE preview'. This makes the tool's purpose immediately clear and unique among the large sibling set.

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 positions build_parse as the free preview of get_leads, implying use for composing and testing before purchasing actual leads. It doesn't explicitly exclude alternatives like list_industries, but the 'FREE preview' framing provides clear context. The schema description adds detailed usage rules (explicit selection via preset_id or target_entity+buying_moments, query as label only), further guiding correct usage.

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

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

With no annotations, the description carries the full burden. It explains the tool computes latest-vs-prior change and notes data is public-domain. It mentions pricing but does not disclose rate limits, error handling, or how periods are determined. It does not contradict any 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 three sentences, front-loads the purpose, and each sentence adds value: problem statement, computation explanation, filter/return summary including pricing. 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?

Given 9 parameters and no output schema, the description covers the main computation, defaults, and return columns. It lacks edge-case explanations (e.g., missing prior periods) but is fairly complete for its complexity.

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

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

Schema coverage is 100% with minimal descriptions. The description adds meaning by specifying default measure (OP_18b), default direction (worse), and the returned fields (latest_score, prior_score, delta, pct_change). This enhances understanding beyond 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 starts with a clear question 'Which hospitals' emergency-department throughput is degrading period-over-period?' and then explains the tool computes changes between periods. It distinguishes from sibling cms_timely_care_search by focusing on period-over-period delta rather than raw snapshots.

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 mentions 'the founder's ED-staffing-pressure tell' implying a use case but does not explicitly state when to use this tool versus alternatives like cms_timely_care_search. No when-not or exclusions are provided.

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

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

No annotations provided, so description carries full burden. It discloses return fields (score, sample, period, snapshot) and notes it's public-domain, but does not mention auth, rate limits, error handling, or confirm read-only behavior. Adequate 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.

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

Two-sentence description plus pricing note. Front-loaded with the core question, then enumerates filterable fields, then states returns. Every sentence adds value 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?

Given 12 parameters, 100% schema coverage, no output schema, and no annotations, the description is fairly complete. It explains data source (CMS Care Compare) and pricing, and lists key outputs. Could elaborate on output structure but 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% (all 12 parameters have descriptions). The description adds value by listing example measures, hinting at CSV usage for state/facility_id/measure, and mentioning min/max score and latest_only. This goes beyond the schema 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?

Description clearly states verb (search), resource (CMS timely-care measures for hospitals), and scope (emergency department). It lists key parameters and return fields. However, it does not explicitly differentiate from sibling tools like cms_timely_care_delta, so it misses some distinction.

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?

Description implies usage for retrieving timely-care measures by various filters but lacks explicit guidance on when to use this tool versus alternatives or when not to use it. No exclusions or context for selection among 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?

With no annotations, the description carries the full burden. It discloses the tool is paid, third-party enriched, and returns decision-maker details. It also specifies it never returns government records. However, it lacks details on error handling, rate limits, what happens if no decision-maker is found, or authentication specifics beyond the API key.

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 front-loads the main action. It covers all necessary points in a single paragraph. However, it could be slightly more structured (e.g., separate sections for payment, constraints) to improve readability without adding 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?

Given no output schema, the description explicitly states the return values (named person, title, work email, LinkedIn) and a constraint (no government records). This provides sufficient context for the agent to understand what to expect, completing the tool's documentation effectively.

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 baseline is 3. The description adds value by contextualizing parameters: stating company is required, domain is the strongest hint, and listing name, state, title as hints. This helps the agent understand parameter relationships 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 reveals a decision-maker at a target company, including specific attributes (person, title, email, LinkedIn). It distinguishes itself from siblings by mentioning it is third-party enriched and never returns government records, which is unique among the listed tools.

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 conditions for use: it is a paid tool requiring an API key or x402 USDC payment, and it never returns government records. However, it does not explicitly compare to sibling tools like get_leads or other enrichment tools, missing an opportunity for when-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?

With no annotations provided, the description carries the full burden. It discloses ordering by handler-id, cursor pagination up to 1000/page, filters available, and that it is a standing roster without per-record registration dates. It also mentions pricing. However, it does not discuss authentication or rate limits, but these are less critical for a read-only feed.

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 dense paragraph, front-loaded with purpose. Every sentence adds value, including pricing. It is slightly long but efficient, with no wasted words.

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

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

Given no output schema, the description lists returned fields (facility, city, state, generator status, roles, NAICS), explains pagination and filters, and mentions pricing. It covers the essential context for a bulk feed tool, though a sample or field types could further improve completeness.

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 has 100% description coverage for all 9 parameters. The description adds contextual grouping (e.g., filterable by state, generator status, NAICS, or flags) but does not provide additional meaning beyond the schema's individual parameter descriptions. According to guidelines, baseline is 3, so this 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 explicitly states it is a bulk feed of the full RCRAInfo handler roster, listing handlers in handler-id order with details like facility, city, state, generator status, roles, and NAICS. It distinguishes from the sibling epa_rcra_handlers_search by being a feed/paginated list versus a search tool.

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 this tool is for bulk retrieval of all handler records with cursor pagination and filtering options. While it does not explicitly state when not to use it or mention alternatives, the context and naming imply it is for comprehensive feed access vs. specific searches.

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?

No annotations are provided, so the description carries the full burden. It discloses public-domain nature, pricing per row, return fields (handler, address, status, roles), and indicates it's a read operation. Does not discuss rate limits or authentication, but these are standard for public APIs. No contradictions.

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

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

The description is four sentences, front-loaded with a question, then capability, then return fields, then pricing. Every sentence adds value with no redundancy or fluff. Well-structured for quick understanding.

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 14 parameters, no output schema, and no annotations, the description covers all relevant aspects: what data is searched, filter options, return fields, and pricing. It also provides business context (EHS vendor universe). Pagination is implied via limit/offset parameters in schema. Complete for a search 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 baseline is 3. The description summarizes filter categories (company, state, etc.) but does not add significant new meaning beyond the schema parameter descriptions. The schema descriptions are adequate, so the tool description adds minimal extra 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 starts with a specific question, states the tool searches EPA RCRAInfo for registered hazardous-waste handlers, and distinguishes itself from ECHO by claiming it returns the entire regulated universe. The verb 'search' and resource are clear, and it differentiates from sibling tools like epa_tri_search.

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 one needs RCRA handler data filtered by various criteria. It provides context (e.g., 'EHS vendor's entire regulated universe') but does not explicitly exclude other tools or provide when-not-to-use guidance. Lacks explicit alternatives naming.

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?

With no annotations provided, the description carries the full burden. It discloses the data is public-domain and self-reported, mentions pricing ($0.05/row), and implies read-only usage. It does not mention rate limits, authentication, or pagination behavior, but the nature of a search tool is reasonably clear. 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 packed into four sentences that are front-loaded with the core purpose, followed by detail on filters, output, and caveats. It is efficient but could potentially be tightened slightly without loss.

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 lack of an output schema, the description adequately explains the return fields (facility, parent company, chemical, release totals) and provides pricing and source context. With 15 parameters, it covers the main usage scenarios. Minor omission: no mention of sorting or pagination behavior in the description, though those are 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?

Schema description coverage is 100%, but the description adds context beyond parameter names: it explains that results are 'entity-resolved where possible', includes parent company and release totals, and notes that amounts are self-reported. This enhances understanding beyond the parameter descriptions 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 starts with a clear question, specifies the EPA TRI Basic Data source, enumerates the many filter dimensions (facility, company, state, chemical, etc.), and states what is returned (facility, parent company, chemical, release totals). It thoroughly distinguishes this tool from sibling tools that cover other regulatory domains.

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 notes the tool is for 'environmental, remediation, and EHS sellers' but does not explicitly state when to use this tool versus siblings (e.g., epa_rcra_handlers_search). No when-not-to-use or alternative recommendations are provided.

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

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

No annotations are provided, so the description carries full burden. It discloses the source (FAA public-domain records), pricing ($0.05/row), and return contents. However, it does not explicitly state the tool is read-only or mention rate limits. Given the search nature and public data, this is adequate 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.

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

The description is a single dense paragraph that packs a lot of information without waste. It front-loads the purpose. While slightly lengthy, every sentence adds value. It could be broken into bullets for clarity, but remains concise.

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 16 parameters with full schema coverage, no output schema, and no required params, the description explains what is returned (aircraft make/model/type/year/seats, registrant), sets expectations with pricing, and covers key search dimensions. It is sufficient for an agent to understand the tool's output and use.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining parameter codes (e.g., type_registrant: 1 individual, 3 corp, 7 LLC) and contextual hints (e.g., registered_since as 'new-ownership tell'). It enhances understanding beyond schema examples.

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's purpose: searching the FAA aircraft registry by multiple criteria. It lists specific fields (owner, N-number, manufacturer, etc.) and states what is returned (aircraft details and registrant). This distinguishes it from sibling tools like faa_deregistrations_search.

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 any FAA aircraft registry query, listing many search parameters and highlighting use cases like new registrations via 'registered_since'. It does not explicitly state when not to use it or compare with alternatives, but the context of sibling tools suggests differentiation.

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?

With no annotations, the description carries the burden. It discloses data source, cost, cancel date constraint (>=2022), and what is returned. It does not cover rate limits or auth but is fairly transparent 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.

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

The description is front-loaded with a question and efficiently covers purpose, use case, returns, and cost. It is slightly verbose but each 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 no output schema, the description adequately describes what is returned, search criteria, and source. It lacks pagination behavior details but is mostly complete for a search tool with 10 optional parameters.

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 detailed parameter descriptions. The description adds no new semantic information beyond listing some search criteria, 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 clearly states the tool searches FAA aircraft deregistrations with a specific verb and resource. It distinguishes from siblings like faa_aircraft_search by focusing on deregistrations (ownership-exit events) and lists key search criteria.

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 use, targeting auctioneers, dealers, and asset-based lenders. It implies the tool is for ownership-exit events but 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.

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

No annotations are provided, so the description carries the burden. It states the tool is read-only (FCC public-domain records) and mentions cost per row. However, it does not disclose other behaviors like idempotency, rate limits, or whether it modifies data. The description is adequate but could add more safety 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 long, with the purpose front-loaded. Every word adds value: it states the function, filter categories, returns, and cost. No wasted text.

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

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

For a complex tool with 15 parameters and no output schema, the description covers the main filter groups and return fields. It explains the pricing and data source. However, it omits pagination details and behavior for unspecified parameters, but the schema partially fills that 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%, and the description adds value beyond the schema by explaining what each parameter filters (e.g., 'granted_since surfaces new license grants') and summarizing the return data. This helps the agent understand how parameters relate to the output.

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 FCC ULS license transactions and specifies what it returns (license, entity-resolved licensee, radio service, status, dates). It uses specific verbs and resources, distinguishing it from siblings that focus on other government 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?

The description lists many filter parameters but does not explicitly state when to use this tool versus alternatives or when not to use it. Among siblings, no other tool searches FCC licenses, so it is implicitly the tool for that purpose, but guidance on exclusion is missing.

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?

No annotations are provided, so the description carries the full burden. It discloses important behavioral traits: the data source ('openFDA public-domain records'), pricing ('$0.05/row'), and entity resolution for applicant companies. It also lists the returned fields (brand, ingredient, dosage, approval dates). No contradictions or hidden side effects are noted.

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

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

The description is four sentences, each adding value. The first sentence sets the context, the second lists search fields, the third describes the output, and the fourth provides source and pricing. It is front-loaded and efficient, though the sentence about returns could be slightly more concise.

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 10 parameters (none required) and no output schema, the description covers purpose, search criteria, return fields, and even pricing and data source. It is complete enough for an agent to understand when and how to use the tool, though a few more details on typical output structure would be beneficial.

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 minimal new meaning beyond the schema: it groups parameters by category (sponsor company, application type, etc.) and mentions 'suffix/punctuation-insensitive' for company, which is already in the schema. It does not significantly enhance understanding of the 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 a targeted question ('Which companies just won an FDA drug approval or supplement?') and clearly identifies the resource as FDA drug approvals/supplements. It lists specific searchable fields (sponsor company, application type, route, etc.) and distinguishes itself from sibling tools like fda_clearances_devices and fda_recalls_search by focusing exclusively on drugs.

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

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

The description explicitly states the searchable criteria and the intended use case ('a day-one commercial/partnership target list for pharma sellers and CROs'). While it does not directly state when not to use or name alternatives, the sibling tools are in different domains (devices, recalls, warning letters), so the usage context is implicitly 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?

With no annotations provided, the description carries the full burden. It discloses that data comes from openFDA public-domain records, returns specific fields, and mentions entity resolution. However, it does not state whether the tool is read-only, any rate limits, or error behavior. The price mention adds 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 two sentences, front-loaded with an engaging question. It efficiently conveys purpose, filtering options, output, source, and price. Every sentence is informative, though the second sentence is somewhat dense. It could be slightly more concise without losing content.

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

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

Given the 10 parameters (all described in schema), no annotations, and no output schema, the description covers the main use case, filters, and output. It mentions the data source (openFDA) and price. It lacks details on pagination or error handling, but these are reasonable omissions. The description is complete enough for an agent to understand the tool's function.

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 each parameter. The description adds value by stating the output fields (applicant company, device name, product code, decision date) which are not in the schema. It also clarifies the 'company' parameter with 'suffix/punctuation-insensitive' and 'entity-resolved where possible', going 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 purpose: searching FDA device 510(k) clearances and PMA approvals by various criteria. It distinguishes itself from siblings like fda_approvals_drugs and fda_recalls_search by specifying 'device' and 'medical device'. It also mentions specific outputs and target users.

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: it answers 'Which companies just cleared or got FDA approval for a medical device?' and lists filtering options. It implies when to use this tool via the question and the 'fresh target list for sellers' phrase. However, it does not explicitly state when not to use it or mention 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?

With no annotations, the description carries the full burden. It discloses the sorting order (newest-first), pagination (cursor, up to 1000/page), filtering options, and pricing ($0.05/row). It also notes the data is observational and not a clinical recommendation. However, it does not mention rate limits, authentication requirements, or whether the tool is read-only.

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 an engaging question, then clearly states the purpose and capabilities. While not extremely concise, every sentence adds value. The pricing is noted at the end. It could be slightly shorter but 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 feed tool with 6 optional parameters and no output schema, the description lists the output fields (sponsor, application number/type, brand names, etc.), explains pagination and filtering, and mentions pricing. It provides sufficient context for an agent to understand what the tool returns and how to use 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?

The input schema has 100% description coverage, so each parameter is already documented. The tool description reiterates the filterable fields and adds enum values for submission_type (ORIG/SUPPL), but does not add significant new meaning 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 it is a bulk feed over openFDA Drugs@FDA approvals, sorted newest-first by approval date. It specifies the resource (FDA approvals) and the action (bulk feed with cursor pagination). This distinguishes it from sibling tools like fda_approvals_drugs (search) and fda_feed_clearances (devices).

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 obtaining recent approvals in bulk, but does not explicitly state when to use this tool versus alternatives like fda_approvals_drugs or fda_feed_clearances. It provides context for pagination and filtering but lacks direct comparison or exclusion criteria.

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?

With no annotations, the description carries full burden. It discloses the data source (openFDA), ordering, pagination (cursor-based, up to 1000), filtering capabilities, and row contents. It also mentions pricing ($0.05/row) and that it is observational and not a recommendation. This provides good behavioral context beyond the 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?

The description is well-structured, front-loading the core purpose and then detailing pagination, filtering, row content, and disclaimer. Each sentence adds value, though it is somewhat lengthy. It could be slightly more concise but remains effective.

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

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

Given 8 parameters with full schema coverage and no output schema, the description adequately explains the feed operation, pagination, filtering, and row contents. It mentions the data source and a disclaimer. It could improve by specifying the exact return format, but it is largely 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%, so baseline is 3. The description adds context about cursor pagination and feed behavior but does not significantly enhance parameter meaning beyond the schema's descriptions (e.g., 'Rows per page (default 500, cap 1000).').

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 provides a bulk feed of FDA 510(k) clearances and PMA approvals, ordered newest-first. It specifies the verb (feed/query), resource (devices cleared or approved), and distinguishes from sibling tools like fda_clearances_devices by emphasizing 'bulk feed' and 'cursor-paginated'.

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 retrieving the latest clearances in bulk and mentions filtering options. It includes a caution about public records being non-recommendations. However, it does not explicitly compare to alternative tools 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.

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

Without annotations, the description fully carries the burden. It discloses cursor-pagination, filtering, ordering (newest-first), and observational nature. It also includes pricing, which is useful. Minor lacking: no mention of rate limits or auth.

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 reasonably concise at three sentences, front-loaded with the core question. Every sentence adds value, though it could be slightly tighter.

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

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

Despite no output schema or annotations, the description explains the purpose, output fields, filtering, pagination, constraints, and pricing. It is comprehensive for a feed 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 coverage is 100%, so baseline is 3. The description adds context by listing returned fields and mentioning filters, but doesn't add significant meaning beyond what the parameter descriptions already provide.

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's a bulk feed of FDA Warning Letters, newest-first, with specific fields. It distinguishes from sibling `fda_warningletters_search` by emphasizing it's a feed and observational.

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 bulk listing and filtering, but doesn't explicitly say when to use this feed vs. the search sibling. It mentions 'Bulk feed' but lacks direct guidance on 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?

No annotations provided, so description carries the burden. It mentions 'observational' and 'public-domain records', indicating read-only nature, but lacks details on pagination, data freshness, or rate limits. Adequate but not thorough.

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

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

The description is information-dense but well-structured, starting with a question and covering source, filters, outputs, and price. Slightly lengthy but each sentence adds value.

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

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

For a search tool with 10 parameters and no output schema, the description lists output fields, source, and pricing. It adequately prepares the agent for usage, though could detail return structure more.

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?

Parameters are fully covered in the schema (100% coverage). The description adds value by grouping filter types (e.g., 'by recalling firm, product type...') and summarizing the search capability, going beyond mere schema repetition.

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 searches openFDA enforcement reports by recalling firm, product type, classification, etc., and lists the output fields. It distinguishes from sibling FDA tools like fda_approvals_drugs and fda_warningletters_search by focusing specifically on recalls.

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 (for recall information) and lists available filters, but does not explicitly exclude cases or name alternatives. Context from sibling tool names provides differentiation.

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?

No annotations, but description discloses return fields, pricing ($0.05/row), and the fact that it returns compliance gaps. Does not explicitly state read-only, but context implies it.

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

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

Single paragraph of ~100 words, front-loaded with key purpose, covers filters, return fields, and pricing efficiently. Could be slightly more structured but overall concise.

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 12 parameters, no output schema, and no annotations, description provides a good overview: purpose, filters, return fields, and pricing. Missing pagination details but offset is in 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 baseline is 3. Description provides overall context but does not add per-parameter meaning beyond schema 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?

Description clearly states 'search the FDA Warning Letters index' with specific verb and resource, and lists available filters, distinguishing it from sibling FDA tools like approvals or recalls.

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 explicit guidance on when to use this tool versus alternatives, but the description implies its use for FDA warning letter data. Lacks 'when not to use' or prerequisites.

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?

No annotations are provided, so the description carries full burden. It discloses that the source is public records, not a consumer report (no FCRA use), mentions match tiers and confidence, and notes pricing ($0.25/call). This gives good transparency about the tool's nature and constraints.

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 long, each adding value: the first explains the tool's action and output sections, the second adds disclaimers and pricing. While a touch verbose, it remains efficient and front-loaded with key 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?

With one required parameter and no output schema, the description adequately summarizes the output sections (OFLC, WHD, OSHA, EPA, FMCSA, LEIE/SAM) and mentions confidence/vintages. It provides a solid high-level overview for an agent to decide whether to use this 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?

The schema covers 100% of parameters, but the description adds meaningful context: the entityId is a UUID from specific search endpoints, and an example format is provided. This helps the agent understand where the value comes from and its required format 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 it returns a 'business360 dossier' for an exact employer entity, specifying it compiles canonical identity and per-source sections from multiple federal databases. This distinguishes it from sibling tools like firmstanding_company_search (search) and firmstanding_business360_lookup (likely a different lookup).

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 tells the agent to use the entity UUID obtained from specific endpoints (/v1/companies/search or /v1/business360/lookup) and implies it is for a known entity. While it doesn't explicitly list when not to use or compare with siblings, the context of sibling tools (e.g., domain-specific tools for EPA, FAA) provides implicit 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?

With no annotations, the description fully discloses behavioral aspects: name/address matching, match tiers and confidence disclosed, public records nature, and pricing. No contradictions.

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

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

The description is a single paragraph that efficiently conveys purpose, sources, and caveats. It is front-loaded with the key use. Slightly verbose but well-structured for the information density.

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 has only 2 simple params and no output schema, the description provides sufficient context: what datasets are covered, matching methodology, confidence disclosure, and legal disclaimers. An agent can confidently select and invoke this 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 coverage is 100%. The description adds context about name normalization (legal suffixes normalized away, case insensitive) and state being a two-letter code, which enhances understanding beyond the schema's brief examples.

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 aggregates federal records across multiple datasets for a company, using name and state. It distinguishes itself from per-dataset sibling tools by being a 'flagship employer dossier' that provides a unified view.

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 what the tool does (employer dossier by name+state), lists included data sources, and clarifies it is not a consumer report (no FCRA use). This helps an agent understand when to use it versus specialized tools like oflc_sponsor_dossier or osha inspections.

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?

With no annotations, the description takes on full burden. It discloses name matching behavior (suffix/punctuation-insensitive, trigram-indexed), the 1000 cap, and that it is not a consumer report (no FCRA use). Pricing is also noted. Missing details on timeout or exact response structure, but overall informative.

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 (4 sentences), front-loaded with the purpose, and each sentence adds essential information: purpose, matching details, output, cap warning, and pricing. No redundant or missing parts.

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 sufficiently describes return fields (entity IDs, identity, address, source/record counts). It also covers the cap and pricing. Could be more complete with pagination behavior or data recency, but it is adequate for an agent to use 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% with descriptions and examples for all 9 parameters. The description adds context beyond the schema, such as the matching normalization and the meaning of 'source'. This helps an agent select correct values.

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

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

The description opens with a clear question and states it searches 3.7M employer entities by name and various filters. It specifies the resource (federal enforcement and compliance records) and the action (search), distinguishing it from sibling tools like firmstanding_business360 which retrieves a specific dossier.

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: what entities are searched, what is returned, and a warning about the 1000 cap. It also notes the pricing model. However, it does not explicitly mention when to use this tool vs. alternatives such as firmstanding_business360_lookup or other search tools, though the purpose is distinct enough.

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?

With no annotations, the description carries the full burden. It discloses key behavioral traits: returns one row per subject, includes counts, dates, and details, mentions data sources (WARN, Form 5500, etc.), and clarifies it is not a consumer report (no FCRA use). However, it does not discuss pagination behavior beyond listing the cursor parameter.

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 paragraph that front-loads the core purpose. It is information-dense but not overly verbose. Every sentence adds value, though it could be more structured with bullet points for clarity.

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 lack of an output schema, the description adequately explains what the tool returns: rows with per-marker counts, dates, and details. It also covers identifier mapping (ticker/CIK) and basis disclosure. The pricing note is a contextual bonus. No gaps remain for an agent to understand the tool's output.

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% (every parameter has a description). The description adds context about marker types and output, but does not substantially enhance parameter meaning beyond the schema. For example, the 'marker' parameter's allowed values are already listed in the schema description, and the description merely restates 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 clearly states the tool's purpose: 'Which businesses carry public-record distress markers?' It lists the ten specific marker types and explains the output structure, distinguishing it from sibling tools like firmstanding_business360 or firmstanding_company_search by focusing solely on distress markers.

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 specify when to use this tool versus alternatives, nor does it provide exclusion criteria. It implicitly indicates its niche (distress markers) but lacks contrast with sibling tools or guidance on when to choose it over other firmstanding tools.

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

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

No annotations are provided, so the description carries the full burden. It details the types of records included, cursor pagination (up to 1000/page), entity graph matching with tier/confidence, and pricing. This is quite transparent, though it omits rate limits and authentication requirements.

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 information-dense, covering agencies, data fields, pagination, entity matching, and legal disclaimer in a single sentence. It is front-loaded with the key question and contains no wasted words.

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

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

Given the 6 parameters, full schema coverage, and no output schema, the description provides sufficient context: pagination behavior, default and max limits, entity matching, and source agencies. It is complete enough for an agent to use effectively.

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 each parameter. The description adds high-level context (e.g., 'since a given date') but does not significantly enhance individual parameter understanding 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 clearly states the tool provides a bulk feed of federal enforcement actions from OSHA, EPA, and DOL WHD with specific fields. It distinguishes from siblings like `firmstanding_screen_enforcement` and `firmstanding_feed_distress` by mentioning 'bulk feed' and the specific agencies.

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 starts with a question ('Which employers were hit with new federal enforcement actions since a given date?') that guides usage. It includes legal disclaimers (public records, not FCRA). While it does not explicitly state when not to use it or compare to siblings, the context is clear enough for an 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?

In the absence of annotations, the description provides behavioral details: it uses public records, name/address-matched, discloses match tiers and confidence, and specifies the verdict and per-source counts. It does not mention side effects or authentication needs, but these are not critical for a read-only data lookup.

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, starting with a clear question, then detailing the scope, output fields, and a usage note. Every sentence adds value with no 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?

Since there is no output schema, the description must explain the return values, and it does so thoroughly: per-source counts, severity totals, action dates, match tiers, and confidence. Combined with the schema for inputs, the description provides complete context for correct tool invocation.

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

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

The input schema already has good descriptions (100% coverage). The description adds context: name should be normalized (legal suffixes and punctuation normalized), state is the employer's keyed state. This extra detail helps the agent understand parameter formatting 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 purpose: to check if an employer has federal enforcement history (WHD, OSHA, EPA). It specifies the input (company name and state) and the output (counts, severity totals, etc.). The name and description distinguish it from siblings like firmstanding_screen_exclusions.

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 tells when to use: to screen an employer's enforcement history with a single call. It also notes it is not a consumer report and not for FCRA use. However, it does not explicitly compare to alternative tools 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.

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

Discloses key behaviors: one-call screen, name normalization, per-list counts, records with details, match confidence, and public records nature. Without annotations, the description carries the full burden and is adequately transparent.

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?

Efficient single paragraph with front-loaded purpose, covering output, restrictions, and price. Could be slightly more structured but is concise and informative.

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

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

Despite no output schema, the description details the return structure (verdict, counts, records) and confirms the tool's scope. Inputs are fully covered by schema. Complete for a straightforward query 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 coverage is 100% and the description adds minimal value beyond the schema (e.g., mentions normalization but schema already states it). 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 screens companies against federal exclusion and debarment lists (HHS OIG LEIE, SAM.gov) and distinguishes from siblings like ofac_screen_sanctions by specifying the lists and FCRA disclaimer.

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 a usage limitation (not for FCRA-regulated use) but does not explicitly compare to alternatives or state when to use this tool over similar ones like ofac_screen_sanctions.

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?

No annotations are provided, so the description carries full responsibility. It discloses that the tool returns aggregate counts and mentions the call cost ($0.001/call). Since it has no parameters and is clearly a read-only statistics endpoint, the description sufficiently conveys the non-destructive nature. However, it does not explicitly state idempotency or side-effect absence.

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 remarkably concise: two sentences that front-load the core question and then enumerate specific aggregates. Every word serves a purpose, including the pricing note. There is no fluff or repetition.

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

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

Given no output schema, the description adequately lists the key output elements (resolved entities, source coverage, record links, raw records). However, it does not specify the return format (e.g., JSON structure) or provide examples. For a simple stats endpoint, this is sufficient but could be slightly more formal.

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 has zero parameters, so the description naturally doesn't need to explain parameter meaning. According to guidelines, baseline for 0 parameters is 4. The description adds value by detailing the output fields, which is more relevant than parameter semantics in this case.

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: providing aggregate statistics about the FirmStanding employer entity graph. It asks 'How big is the FirmStanding employer entity graph right now?' and enumerates the specific aggregates (resolved entities, sources coverage, record links, raw records). This distinguishes it from sibling tools like firmstanding_company_search that focus on individual companies.

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 obtaining overall graph statistics but does not explicitly state when to use this tool versus alternatives. No guidance on when not to use or prerequisites is provided. The purpose is self-explanatory, but clarity on exclusion criteria is lacking.

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?

No annotations are provided, so the description carries full burden. It notes pricing ($0.25/call) and states 'in one call', implying a single request. However, it does not disclose read-only nature, rate limits, or potential response size. The behavioral details are adequate 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.

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

Description is a single dense but informative sentence listing all data components. It is not overly verbose and covers key points efficiently. Minor improvement could be structuring as a bullet list, but current form is acceptable.

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 thoroughly enumerates return data sections (census, authority history, insurance, safety rating, SaferGrade breakdown, inspection/crash summaries, timeline). It omits some interpretation details but is sufficient for domain users. Sibling tools provide context for alternatives.

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?

Only one parameter (usdot) with schema description providing example and type. Description does not add significant meaning beyond the schema. Since schema coverage is 100% and parameter is straightforward, 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?

Description clearly states it returns a comprehensive FMCSA dossier for a carrier by USDOT number, listing specific data components (census identity, authority records, insurance, safety rating, SaferGrade, inspections, crashes). This distinguishes it from sibling tools like fmcsa_carrier_lookup or fmcsa_carrier_score which focus on individual aspects.

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?

Description implies this is the one-call complete file, suggesting use when a full picture is needed. While it does not explicitly list alternatives or exclusions, the sibling tools' names and this description provide enough context for selection.

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

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

No annotations provided, so description carries burden. It indicates a read-only lookup and mentions pricing, but does not discuss side effects, authentication, rate limits, or any other behavioral traits beyond that.

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?

Description is front-loaded with the main question, then lists fields and pricing. It is concise but slightly verbose with the list; still effective and 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 single-parameter tool with no output schema, the description adequately explains what the tool does and what it returns. Missing error handling or no-result behavior, but overall complete for typical use.

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

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

Schema coverage is 100% (usdot parameter described), but description adds value by explaining that the parameter is a USDOT number and what the tool will return (list of fields). This goes beyond the schema's description.

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

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

The description explicitly states it looks up FMCSA census record by USDOT number, lists specific fields returned (name, address, fleet size, etc.), and distinguishes from sibling tools like search or vet by focusing on registration-of-record details.

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

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

The description implies the tool is for identifying a carrier by USDOT number but does not explicitly mention when to use this vs alternatives like fmcsa_carrier_search or fmcsa_carrier_vet. No exclusions or context for choice.

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?

No annotations are provided, so the description carries full burden. It clearly describes the output (score, grade, confidence, inputs) and includes pricing. Although it does not explicitly state read-only behavior, the nature of the tool (returning a score) implies no side effects. The description is transparent enough for a simple query tool.

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 extremely concise: two sentences that front-load the core purpose, followed by a detailed list of returned components and pricing. No redundant information exists.

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 input (single parameter) and no output schema, the description completely covers what the tool returns and how it behaves. Every component of the output is listed, making it easy for an agent to understand the tool's value.

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

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

The input schema covers 100% of parameters (one required string usdot with examples and description). The description does not add additional meaning beyond what the schema already provides, leading to a baseline score 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 clearly states the tool returns the SaferGrade score (0-100) along with its components, using a specific verb ('returns') and resource ('score for this carrier'). The output details (letter grade, confidence, inputs) differentiate it clearly from sibling tools like fmcsa_carrier_lookup or fmcsa_carrier360.

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 retrieving a carrier's safety score, but does not explicitly state when to use this tool versus alternatives like fmcsa_carrier360 or fmcsa_carrier_vet. The context is clear, but explicit guidance on when-not-to-use would improve the 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?

With no annotations, the description carries the full burden. It reveals trigram name search (case-insensitive), ordering by largest fleets first, a row cap of 100, total_matched cap of 1000, and pricing ($0.05/row). It also explains the meaning of total_matched_capped. This provides good behavioral insight, though auth and rate limits are not mentioned.

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 extremely concise: two sentences covering purpose, mechanism, use cases, limits, and pricing. Front-loaded with a question summarizing functionality, with no redundancy or unnecessary 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?

Given the complexity of 10 parameters and no output schema, the description covers the essential aspects: what the tool does, key filters, default ordering, limits, and cap behavior. It does not describe the output fields, but the mention of 'carrier's USDOT number' implies an output expectation. It is largely complete for an agent to use 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 has 100% coverage with descriptions and examples for all 10 parameters. The description adds some high-level context (e.g., trigram match for name, pricing per row related to limit) but does not significantly expand on individual parameter meanings. Baseline 3 is appropriate as schema already documents parameters well.

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 is a search tool for FMCSA-registered carriers, using trigram name search over 4.4M+ records, with multiple filter criteria and specific use cases. It effectively distinguishes from siblings like fmcsa_carrier_lookup (single carrier lookup) and fmcsa_carrier360 (comprehensive view), as those are not search tools.

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

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

The description provides explicit use cases (find a carrier's USDOT number, shortlist carriers in a lane state, screen brokers vs carriers) and hints at when to narrow filters (when total_matched_capped is true). However, it does not directly compare to sibling tools, though the sibling names imply different purposes.

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?

No annotations are provided, so the description carries full burden. It lists what the tool returns (census, authority, insurance, score, history), implying it is a read-only screen. However, it does not explicitly state permissions, side effects, or whether it is read-only, making it adequate but not fully transparent.

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

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

The description is a single sentence with an embedded price note, which is slightly extraneous. It is front-loaded with the use case and efficiently conveys the tool's 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 simple tool with one parameter and no output schema, the description thoroughly explains the tool's return value (five data categories). It fully satisfies the information need for an agent to invoke the tool correctly.

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

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

Schema coverage is 100% with a description and example for the single 'usdot' parameter. The description adds no additional meaning beyond what the schema provides, 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 clearly states the tool is for vetting a carrier before tendering a load, listing specific data points (FMCSA census, operating authority, insurance, SaferGrade, crash history). It distinguishes from sibling tools like carrier lookup or score by focusing on a comprehensive onboarding check.

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 opening question 'Is this carrier's paperwork in order before I tender a load?' explicitly indicates the primary use case. It does not discuss when not to use or mention alternatives, but the context is clear enough for an agent to decide.

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

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

The description discloses cursor-based pagination, row limit, filtering capabilities, and pricing per row. It does not mention rate limits, default parameters, or error handling, but for a read-only feed tool, the disclosed behaviors are adequate. No annotations are present, so the description carries the full 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 a single sentence that efficiently conveys the purpose, data fields, pagination, and filters. It is front-loaded with a question that clarifies intent. However, the list of fields is somewhat lengthy within the sentence, reducing scanability slightly.

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 5 parameters with full schema coverage and no output schema, the description covers the key aspects: what data is returned, pagination method, filters, and pricing. It lacks explicit mention of default row count (500 from schema) and error behavior, but these are minor gaps for a well-described feed 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 coverage is 100%, but the description adds value by explaining the cursor's opaque nature, the meaning of added_since date field, and the cap of 1000 rows per page. It reinforces the filtering options with context relevant to the data feed.

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

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

The description clearly states the tool provides the full FMCSA carrier census with authority and safety context, listing the types of data included. It distinguishes from sibling tools by emphasizing 'bulk analytics feed' and cursor-pagination for large-scale retrieval. However, it does not explicitly differentiate from similar FMCSA tools like fmcsa_carrier_search.

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 bulk analytics and enumerates filtering options, but lacks explicit guidance on when to use this tool versus alternatives. It does not mention when not to use it or provide context about alternatives among the FMCSA sibling tools.

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

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

With no annotations, the description carries full burden for behavioral disclosure. It clearly states it returns aggregate statistics (not individual records), lists the data categories included, and mentions the cost. It does not explicitly say it's read-only, but the nature of 'headline aggregates' implies no side effects. A slight gap is not stating whether it refreshes or is cached.

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 extremely concise: a single sentence front-loaded with the core question, followed by a bullet list of outputs. Every phrase earns its place. The price note is a helpful addition without clutter.

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 parameters and no output schema, the description adequately explains what the tool returns. It covers key aggregates a user would expect. However, it could briefly mention the output format (e.g., JSON object) or if pagination is needed, though for a stats endpoint this is likely fixed. Still, it is sufficiently complete for a zero-parameter stats 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?

The tool has zero parameters, so the schema already fully defines the input. The description does not need to add parameter meaning. Baseline of 4 is appropriate as there is no additional information required or provided.

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 starts with a clear question 'How big is the FMCSA carrier dataset right now?' and lists specific headline aggregates (total/active carriers, SaferGrade distribution, inspection/crash history, out-of-service rates). It immediately distinguishes from sibling tools that focus on individual carrier details, making the 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?

The description does not explicitly state when to use this tool versus alternatives. While the name 'stats' and sibling tools like 'fmcsa_carrier_search' imply it's for aggregate data, there is no direct guidance on when to choose this over other FMCSA tools or what conditions warrant its 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?

Without annotations, the description discloses key behavioral traits: returns entity-resolved establishments with address, activities, size; mentions price ($0.05/row); and states it's from FSIS public-domain records. It does not cover rate limits or modify behavior, but the read-only nature is implied.

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 efficiently convey purpose, return values, and source/price. Front-loaded with key information, no wasted words.

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

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

Given 14 parameters and no output schema or annotations, the description covers purpose, return fields, and data source. It lacks explicit pagination details but is sufficient for a search tool. Could mention default sort or limit behavior.

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 has 100% description coverage, so the baseline is 3. The description summarizes searchable fields but does not add new semantic meaning beyond what the schema already provides for individual parameters.

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

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

The description clearly states the verb 'Search' and the resource 'USDA FSIS Meat, Poultry & Egg Product Inspection Directory' with specific searchable fields. It distinguishes itself from sibling tools like fsis_recalls_search by focusing on establishments rather than recalls.

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 on when to use ('which plants operate in a market') and contrasts with 'not just OSHA-hit plants', implicitly guiding the agent away from more specialized search tools. However, it does not explicitly mention sibling tools 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?

No annotations provided, so description carries full burden. Describes return fields ('recalling firm, classification, reason, product, dates') and mentions use case and pricing. However, lacks disclosure on authorization, rate limits, or potential side effects.

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?

Single paragraph front-loaded with purpose, listing criteria, return fields, and use case. Not overly verbose; each part adds value. Could be slightly more 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 search tool with no output schema, description covers key inputs, outputs, and use case. Minor gaps: pagination details (limit/offset) not mentioned, and no error handling or output format hints.

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 detailed descriptions and examples for all 12 parameters. The description adds minimal new semantic meaning beyond summarizing filter capabilities. 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?

Description starts with a clear question and states 'Search USDA FSIS recall and public-health-alert records' with specific resource type (meat/poultry/egg) and domain (FSIS). It is distinct from sibling tools like fsis_establishments_search.

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?

Lists many filter criteria (firm, classification, reason, state, active, outbreak, date) and states what it returns. Does not explicitly exclude cases or mention alternatives, but 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?

Since no annotations are provided, the description fully bears the burden. It explicitly discloses that the tool returns a signed attestation and mentions the price ($0.001/call). It does not claim any destructive side effects, and for a health check, this is sufficient transparency. However, it could explicitly state it is read-only or non-mutating, preventing full marks.

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 extremely concise—two sentences that front-load the core purpose (health check, datasets) and add the key behavioral detail (attestation) and cost. Every sentence serves a clear purpose 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?

Given the tool has no parameters, no output schema, and is a simple health check, the description covers all necessary context: what it does, what it returns (attestation), and cost. It is complete for its 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 tool has zero parameters, and the schema description coverage is 100% (no parameters to describe). According to guidelines, baseline for 0 params is 4. The description adds no parameter information, but none is needed.

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 checks if the Govparse Agent Gateway is up and identifies fronting datasets. It uses the question form to convey purpose and the mention of 'signed _meta attestation' specifies what is returned. No sibling tool serves a similar health-check function, so it is well-differentiated.

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

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

The description implies the tool is for verifying gateway status and pipeline integrity, but it does not explicitly state when to use it versus alternatives or when not to use it. Given no sibling tools overlap, the implicit guidance is adequate but not 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?

With no annotations provided, the description carries full burden and meets it well. It discloses the tool is PAID and priced per lead returned, explains the payment methods (API key or x402 USDC prepaid up to `limit`), clarifies that `query` alone does not select a Parse, and explicitly states it returns 'real rows' rather than a preview. This is high-value behavioral context beyond the 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?

The description is three sentences with no filler: it front-loads the purpose, then covers cost/payment, then gives the workflow prerequisite. Every sentence contributes essential information, making it appropriately sized and 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 tool with 10 parameters, no annotations, and no output schema, the description provides enough context for an agent to understand what to expect: actual companies, events, and contacts. It also explains the prerequisite workflow and pricing model. The schema covers all parameter details. It lacks an explicit return schema or pagination behavior, but the given context is sufficient for 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 description coverage is 100% with detailed explanations for all 10 parameters, which sets a baseline of 3. The description adds useful semantics by linking `limit` to prepayment ('prepaid for up to `limit` leads') and by clarifying the role of the `parse` parameter in the workflow ('pass its `parse` here'). These are meaningful additions 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 verb and resource: 'Get the actual B2B leads for a Parse'. It specifies what the results include ('matching companies and the public-record events that flagged them, including any free native contacts') and distinguishes itself from the prerequisite build_parse by framing the workflow ('Compose the Parse with build_parse first, then pass its `parse` here').

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 an explicit usage workflow: build the Parse first, then pass its `parse` object. It also explains payment options (API key or USDC) and that the tool is paid per lead. However, it does not explicitly state when not to use this tool or mention alternatives beyond build_parse, such as using preset_id or list_industries directly, which are covered in the schema but not in the description.

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?

No annotations are provided, so the description carries the full burden. It discloses pricing ($0.05/row) and the 'kind' parameter accepts 'contract' or 'assistance' with CSV for both. However, it does not mention behavior like result limits, pagination details beyond schema (offset/limit), or what happens with empty results.

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 paragraph that hooks with a question, then lists parameters and use cases, and ends with pricing. It is reasonably concise but slightly verbose; it could be tightened by removing the hook or merging sentences.

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 13 parameters and no output schema, the description provides sufficient context to understand the tool's purpose, searchable fields, and typical use cases. It is adequate without being exhaustive.

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 and examples for all parameters. The description adds overarching context (e.g., 'competitor award research') but does not add new meaning to individual parameters beyond what the schema already provides.

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

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

The description uses a specific verb ('Search') and resource ('USAspending federal award history'), clearly distinguishing from sibling tools like 'govcon_opportunity_search' (opportunities) and 'govcon_subaward_search' (sub-awards). It lists specific search dimensions (recipient, agency, NAICS, etc.) and use cases (competitor research, incumbent lookup, grant-winner analysis).

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 mentions three use cases (competitor award research, incumbent lookup, grant-winner analysis) and implies the tool covers both contracts and assistance. However, it does not explicitly state when to use alternatives or provide exclusion criteria.

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?

With no annotations, the description carries full burden and does well: it discloses ordering (newest-first), pagination (cursor-based up to 1000/page), filtering options, output fields, and even pricing ($0.05/row). It lacks details on data freshness or update frequency, hence not a 5.

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

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

The description is packed with information and front-loaded with the purpose ('Which companies just won federal money?'). It efficiently covers purpose, pagination, filters, output, and cost. Could be slightly more concise but current length is 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?

Given the tool's complexity (7 optional params, no output schema), the description is fairly complete: it explains pagination, filters, output fields, and pricing. Lacks error handling or rate limit info, but for a feed tool with cursor pagination it is adequate.

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

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

Schema coverage is 100% with descriptions for all 7 parameters. The description summarizes filterable fields (NAICS, agency, min_amount, kind, since) but adds no significant new meaning beyond the schema's existing descriptions. 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 provides a bulk feed of USAspending prime awards, newest-first, with specific filters and output fields. It distinguishes itself from sibling tools like govcon_award_search (search) and govcon_feed_subawards (subawards) by focusing on prime awards as a funded-growth signal.

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 monitoring recent awards ('Which companies just won federal money?') and specifies it's a bulk feed with cursor pagination. While not explicitly stating when not to use, the context from sibling names (e.g., govcon_award_search for specific details) provides sufficient 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?

No annotations provided, so the description fully bears the burden. It discloses the observational nature ('as filed'), pricing ($0.05/row), pagination (cursor, up to 1000/page), and filtering options. It does not explicitly state read-only or auth requirements, but the pricing and public record mention strongly imply it's a read operation.

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 paragraph but front-loads the core value proposition ('Which companies just received...') before detailing attributes. It is information-dense without being overly verbose, though it could be slightly more structured for skimmability.

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?

Without an output schema, the description lists the key fields returned (sub-recipient, prime, agency, amount banded, NAICS, date) and explains pagination and filtering. It provides sufficient context for an AI agent to understand the tool's behavior and output shape, though exact field names and data types are 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?

All 8 parameters are described in the input schema (100% coverage), so baseline is 3. The description adds conceptual value by explaining new_only as 'first-time subawardees' and the meaning of cursor pagination, enhancing understanding beyond 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 provides a bulk feed of federal subawards from USAspending, identifying both current and first-time sub-recipients. It distinctively describes the scope and fields returned, differentiating from sibling tools like govcon_feed_awards (prime awards) and govcon_subaward_search.

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 bulk subaward discovery and filtering, including new_only for first-time subawardees. While it does not explicitly contrast with sibling tools, the context of 'feed' versus 'search' and the mention of cursor pagination give clear signals for expected use cases.

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?

No annotations are provided, so the description carries the full burden. It mentions a price of $0.01/call, but does not explicitly state read-only behavior, auth needs, or rate limits. The context implies it is a read operation, but transparency 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, front-loaded with a natural language question, and includes all essential information in two sentences with no wasted words.

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

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

Given the tool has one parameter and no output schema, the description adequately lists the fields returned. However, it does not describe the output format or structure, which is acceptable but could be improved.

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 description and examples. The description adds value by clarifying that noticeId can be a SAM.gov notice ID or a Grants.gov opportunity ID/number, which is not 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 clearly states it retrieves full details of a federal opportunity, specifying the sources (SAM.gov and Grants.gov) and listing the fields included. It distinguishes from sibling tools like govcon_opportunity_search by focusing on a single record by ID.

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 tells when to use this tool: when you have a specific notice or opportunity ID and want complete details. It implies not for searching, but does not explicitly mention alternatives 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?

No annotations provided, so description carries the burden. It mentions the source (SAM.gov, Grants.gov) and pricing, but does not disclose limitations, rate limits, or behavior on no results. It adequately describes what the tool does but lacks deeper 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 a single, information-dense sentence with a business-focused opening and all key filters enumerated. It includes pricing concisely. No wasted words, but the sentence is somewhat long, bordering on dense.

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 11 parameters and no output schema, the description explains the tool's purpose and inputs well but does not describe the output format or structure. For a search tool, users might need to know what fields are returned. Lacks information on result details.

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 and examples. The description lists filters in narrative form but adds minimal new information beyond the schema. Baseline 3 is appropriate; the description does not significantly compensate beyond what's already in the input 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 starts with a clear business question and states it's a unified search over SAM.gov contract opportunities and Grants.gov postings. It lists all major filters, distinguishing it from sibling tools like govcon_award_search and govcon_opportunity_detail.

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 a clear use case: 'find open federal money that fits us'. It implies when to use this tool (when searching for open opportunities) but does not explicitly state when not to use it or mention alternatives. However, the purpose is distinct enough from 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?

No annotations are provided, so the description carries full burden for behavioral disclosure. It only describes the tool's output, not behavioral traits like read-only nature, rate limits, or effects on data. As a stats tool, it's clearly non-destructive, but this is implicit rather than stated.

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 that front-loads the purpose and covers the key outputs. The price note is appended without clutter. Every part is informative and concise.

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 parameters and no output schema, the description adequately covers the tool's function by listing the three aggregate categories. It could mention specific metrics (e.g., counts, dollar amounts) but already specifies 'active opportunities', 'open deadline', 'status', and 'total dollar amount', which is sufficient for a stats 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?

The input schema has zero parameters with 100% schema description coverage, so the baseline is 4. The description adds context about what the tool returns (three categories of aggregates), which is useful since there are no parameters to explain.

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?

Description clearly specifies it provides headline aggregates of open federal money, including active SAM.gov contract opportunities, Grants.gov opportunities by status, and USAspending award records. It uses a specific verb ('aggregates') and resource ('open federal money'), and distinguishes from sibling tools like govcon_opportunity_search and govcon_opportunity_detail which focus on individual records.

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 high-level overviews ('How much open federal money...'), but does not explicitly state when to use this tool over siblings like govcon_opportunity_search. No when-not-to-use or alternative guidelines are provided, leaving the agent to infer context from the tool's function.

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?

No annotations exist, so the description bears the transparency burden. It mentions public records and pricing but does not disclose result format, pagination behavior beyond limits, or error scenarios.

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 detailed but not overly verbose; it front-loads the purpose and organizes parameters logically. Minor redundancy in examples could 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?

Given 19 parameters and no output schema, the description covers all inputs with examples and clarifications. It lacks return value details but is otherwise thorough for a search 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?

With 100% schema coverage, baseline is 3. The description adds meaningful context: explains CSV usage, prime vs sub terminology, and new_subawardee semantics, enhancing parameter understanding 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 USAspending subawards, specifying the data source (File F prime → sub cascade) and distinguishing it from sibling tools like govcon_award_search by focusing on subawards.

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 extensive parameter guidance with examples and explains specific use cases (e.g., new_subawardee for first-time subawardees). However, it lacks explicit 'when not to use' or direct comparisons to 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?

With no annotations, the description carries full burden. It reveals the read-only nature (search) and mentions pricing and public-domain source. However, it does not disclose the cap on returned rows (limit default 25, max 100) or pagination behavior, which are important for agent expectations.

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 plus a pricing tag, front-loaded with a engaging question. It efficiently conveys data source, filters, outputs, and cost. The opening question, while slightly informal, does not waste space. Could be slightly tighter by removing the question, but it's still effective.

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

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

Given 9 optional parameters and no output schema, the description covers the key filters and outputs but omits details on sorting, pagination, and default behavior. It mentions limit but does not explain offset or sort semantics. Adequate but not complete for complex queries.

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 baseline is 3. The description adds value by listing filterable fields and noting computed outputs, but it does not elaborate on individual parameter syntax or constraints beyond what the schema already provides.

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

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

The description clearly identifies the tool as searching HCRIS S-3 cost reports for staffing metrics. It specifies the data source, available filters (state, CCN, name, etc.), and the exact outputs (FTE, beds, ratios), distinguishing it from generic hospital data tools.

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: it searches flattened HCRIS S-3 records by specified filters. It does not explicitly contrast with siblings like hcris_staffing_decline_search, but the specificity (returning computed ratios) implies its use case for staffing analysis. Lacking explicit when-not guidance prevents 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?

With no annotations, the description carries the full burden. It explains the comparison logic (latest vs prior year), the metric options, filter parameters, and return fields (delta, pct_change). It also notes the dataset provenance (CMS public-domain) and joinability with CMS timely-care. Minor ambiguity remains about how 'latest' and 'prior' are determined across multiple fiscal years.

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 extremely concise: two focused sentences plus a price note. Every word adds value, starting with a compelling question. No 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?

Given 10 parameters and no output schema, the description adequately explains the comparison logic, filter capabilities, and return fields. It could clarify edge cases (e.g., missing prior year data) but overall provides sufficient context for an AI agent to use the tool correctly.

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

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

Schema coverage is 100%, providing a baseline of 3. The description adds value by explaining the default metric (fte_per_bed) and alternative (fte_per_discharge), how parameters like min_pct_drop filter results, and the output fields (latest/prior ratio, delta, pct_change). This contextualizes parameters beyond their schema 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 uses a specific verb ('cut staffing year-over-year') and resource ('HCRIS staffing ratio'), clearly distinguishing it from siblings like 'hcris_cost_reports_search' which deals with cost reports rather than staffing declines.

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 states the tool is for finding hospitals with staffing declines and lists filter parameters. While it implies when to use, it does not explicitly state when not to use or compare with alternatives. However, the context of sibling tools makes the usage clear.

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

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

No annotations provided, so description carries full burden. Discloses pricing ($0.05/row), output fields, and that this is a search tool. Does not mention rate limits or auth, but reasonable for a public data source.

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 concise sentences, front-loaded with purpose, lists key filters, and ends with value proposition. No wasted words.

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

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

Describes output fields and pricing, which complements the 13-parameter schema. Lacks discussion of pagination handling beyond limit/offset, but sufficient for a search tool with no 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 coverage is 100%, so baseline is 3. Description adds marginal value by explaining the buying moment and output fields, but does not add new parameter-level semantics beyond what's 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?

Clearly states the tool searches HRSA HPSAs with specific filters. Uses a question to frame the purpose and lists key parameters, distinguishing it from the sibling 'hrsa_mua_search' which focuses on medically underserved areas.

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 context for use (clinician-staffing, telehealth, workforce vendors) and lists output fields. Does not explicitly state when not to use or name alternatives, but the use case 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?

No annotations provided. The description explains it is a query tool returning specific fields and mentions price per row. It does not declare read-only nature or potential side effects, but the context implies no destructive actions.

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-loaded, immediately stating the tool's purpose. Every sentence adds value, including pricing 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?

With 10 parameters and no output schema, the description mentions key return fields (service area, IMU score, geography, dates) and provides business context. It could be more complete by listing all return fields, but 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?

All parameters are described in the input schema with examples. The description adds value by explaining IMU score meaning (LOWER = more underserved) and date format, going 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 HRSA Medically Underserved Areas/Populations (MUA/P) and lists searchable fields. It distinguishes from sibling hrsa_hpsa_search by focusing on MUA/P 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 specifies searchable criteria and return fields, and mentions use cases (safety-net / FQHC territory). However, it lacks explicit exclusions or comparisons to alternatives like hrsa_hpsa_search, which would improve 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?

With no annotations, the description carries full burden for behavioral traits. It mentions the tool is 'FREE' but does not disclose potential side effects, permissions needed, rate limits, or behavior when the optional parameter is omitted. The description adds minimal behavioral insight beyond the 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?

The description is a single, concise sentence that front-loads the verb 'Discover' and includes all essential information. Every part is relevant, and the structure is 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?

Given the tool's simplicity (one optional parameter, no output schema), the description is adequate but leaves gaps. It explains what the tool returns but does not detail response format, pagination, or error handling. An output schema would improve completeness.

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 a single parameter fully described. The description does not add additional meaning to the parameter itself beyond the schema. The mention of response content (ELI12 explanation, id) is useful but does not pertain to parameter semantics.

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: to discover ParseData's industries and their associated curated Parses. It includes specific details about each parse (plain-language ELI12 explanation and an id for further use), distinguishing it from sibling tools like build_parse and get_leads.

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 that this tool is a starting point for discovering industries before using build_parse/get_leads, but it does not explicitly state when to use it or provide comparisons to alternatives. No exclusion criteria are 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?

No annotations are provided, so the description carries full burden. It discloses that it is a public-domain record search, includes a per-row price, and describes the scope (all coal and metal/non-metal mines under MSHA jurisdiction). It does not mention auth requirements or rate limits but sets appropriate expectations 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.

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

The description is 4 sentences, front-loaded with a question and immediate answer. It efficiently conveys the dataset, searchable fields, return fields, and pricing. No extraneous information; every sentence adds value.

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

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

Given the complexity (18 parameters, no output schema, no annotations), the description explains the dataset jurisdiction, what is returned (mine, operator, controller, commodity, employees, status), and pricing. It lacks output field details but covers the essential scope for a search 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?

The input schema has 100% coverage with descriptions for all 18 parameters. The description merely summarizes the parameter categories (e.g., 'by operator, mine name...') without adding new meaning beyond the schema. Thus it meets the baseline for high 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 it searches the MSHA Mines data set for mines and quarries, specifying the exact resource and actions. It includes context about the dataset (NAICS-21, OSHA-exempt) and lists returned fields, making the purpose unambiguous. The name and description distinguish it from siblings like msha_violations_search.

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 explicit guidance on when to use this tool versus alternatives. It opens with a broad question but does not mention exclusions or conditions under which another tool would be more appropriate. There is no mention of sibling tools or when not to use this one.

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