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

With no annotations, the description fully details behavioral traits: deterministic nature, method priority, capacity derivation, confidence levels, and audit trail. It does not mention edge cases but is highly 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 quite lengthy and dense. While all information is valuable, it could be more concise. Front-loading of purpose is good, but some details could be streamlined.

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, no output schema, and no annotations, the description is exceptionally complete, covering methods, confidence, audit trail, and parameter relationships. It leaves few gaps.

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%, baseline 3. The description adds significant meaning beyond schema, e.g., explaining method selection priority, capacity input hierarchy, and how capacitySource should be used. This extra context raises the score.

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 a 'Deterministic ADV screening calculator for FLSA enterprise-coverage triage' with specific verbs (estimate, screening) and resources (ADV, FLSA flag). It distinguishes from sibling tools by focusing on a niche function not covered by others.

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 usage guidance: 'NOT a coverage determination — screening signal only', method selection priority, and best practice to use employeeCount from OSHA. It lacks explicit alternatives but is clear on when to use this tool.

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

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

No annotations are present, so the description must carry the full burden. The description only states it routes questions but does not disclose behavioral traits such as whether it is read-only, whether it makes multiple API calls, or any side effects. The agent lacks safety cues.

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

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

The description is a single, front-loaded sentence of 22 words that clearly communicates the tool's core function. Every word adds value, and there is no redundancy or fluff.

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

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

For a complex routing tool that delegates to multiple sources, the description provides only a high-level overview. It lacks details on output format, routing logic, or constraints. However, given the absence of an output schema and annotations, it is minimally 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?

The input schema has 100% coverage with clear descriptions for all three parameters (question, dryRun, maxResults). The tool description adds no additional parameter-level meaning beyond what the schema already 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's purpose: routing a plain-English question to the correct government data source (WHD, OSHA, DOL foreign-labor/LCA, SAM.gov). The verb 'route' and specific resource list make it distinct from sibling tools that target individual sources.

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

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

The description implies usage when a user has a general question not specific to a single source, but it does not explicitly state when to use this tool versus the many sibling tools (e.g., whd_enforcement_query, lca_search). No 'when not to use' guidance is provided.

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

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

Discloses source (OpenCorporates), attribution requirement, and output fields (full address, previous names, etc.). No annotations provided, so description carries burden. Missing details on rate limits, failure modes, or data freshness, but provides reasonable 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?

Two sentences, no fluff. First sentence states action and parameters; second sentence adds usage context and output. Every word 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 no output schema, the description usefully lists output fields. It properly references sibling tool for prior step. Lacks details on error handling or rate limits, but is complete enough for a simple lookup tool.

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

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

Schema covers all three parameters with descriptions. The description reiterates jurisdiction and company number but adds no new semantics beyond the schema. DryRun parameter is explained only in 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?

Clearly states the tool looks up one entity by jurisdiction and company number via OpenCorporates, and explicitly distinguishes it from business_entity_search by specifying its use case ('after business_entity_search to get full canonical record').

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

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

Explicitly says to use after business_entity_search, providing clear context. Lacks explicit when not to use or alternatives, but the recommendation is strong and sufficient.

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

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

With no annotations, the description carries full burden. It discloses the external API dependency (OpenCorporates), data lineage audibility, free tier constraints, auto-prefixing for US states, and the existence of a dryRun mode for testing. It does not mention latency or rate limiting, but it provides significant 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, well-structured paragraph that front-loads the primary purpose and key details. Every sentence adds value, though information about free tier limits could be separated. Overall, it is efficient and not overly verbose.

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 9 parameters and no output schema, the description covers what is returned (name, company number, status, etc.), the source and limitations, and parameter behavior. It lacks details on pagination metadata and error handling, but it is largely complete for an agent to invoke correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the auto-prefixing for jurisdictionCode, the use case for dryRun, and that maxResults is capped by OpenCorporates. These details go beyond the schema descriptions and aid correct parameter use.

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 state business registrations via OpenCorporates. It lists specific use cases: mapping trade names, identifying registered agents, finding related entities, confirming active status. The verb 'Search' is precise, and the title indicates the source, distinguishing it from sibling tools like business_entity_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 explains when to use the tool (e.g., for legal entity mapping, registered agent identification) and includes practical guidance on jurisdiction narrowing for US states and free tier limits with API key requirements. It does not explicitly list when not to use it, but the context is clear enough for selection among diverse 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 exist, so the description carries full burden. It discloses the free Census API, no key required, and explains the geocoding and fetch process. However, it lacks explicit error handling details (e.g., when city is not found).

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

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

The description is well-structured with the main action upfront, followed by return fields and usage guidance. It is slightly verbose but every sentence adds necessary 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 the tool's complexity (6 parameters, no output schema), the description adequately explains the returned fields and their purposes (e.g., county FIPS for usaspending_award_search). Some structured output would improve completeness, but it's 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%, so baseline is 3. The description adds value by explaining parameter pairs (e.g., city/state vs placeFips/stateFips) and the dryRun function, providing context 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: 'Look up a US city/town/CDP via the Census geocoder, then fetch its total population from the ACS 5-year estimate.' It lists the returned fields, distinguishing it from siblings like adv_estimate.

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

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

Explicitly advises to 'Use this BEFORE adv_estimate when sizing an enforcement universe or running a restaurant research workflow against an unfamiliar city.' This provides clear when-to-use and when-not-to-use context.

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. The description discloses that no API key is needed, but it does not mention whether the operation is read-only, idempotent, or has any side effects. For a search tool, these are minimal behavioral cues.

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

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

The description is two short sentences with no redundant information. Every element serves a purpose—stating the action and a key access note. 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 and no annotations, the description is minimal. It lacks details about return format, pagination behavior, or which dataset metadata fields are searchable. An agent may not have enough context to use the tool effectively among many sibling search tools.

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 three parameters (limit, agency, search) are fully described in the input schema (100% coverage). The description adds no additional meaning or context beyond what the schema already provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool searches the public DOL v4 datasets catalog. The verb 'search' and resource are specific. However, it does not explicitly differentiate from sibling search tools like lca_search or osha_inspection_search, which all target different data sources.

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

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

The description only notes that no API key is required, which is a usage prerequisite. It provides no guidance on when to use this tool versus alternatives, no context on typical use cases, and no 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 provided, the description carries the full burden. It only says 'read', implying non-destructive operation, but discloses no details about performance, data freshness, or potential limitations.

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, clear sentence with no unnecessary words. It is efficient but could benefit from a bit more detail without becoming verbose.

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 11 parameters and no output schema, the description is too sparse. It fails to explain what the tool returns or how to interpret results, leaving the agent underinformed.

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 11 parameters are documented in the input schema with 100% coverage, so baseline is 3. The description does not add any extra context about how the parameters are used together or special behavior.

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 reads field names from a DOL XLSX file. However, it does not distinguish itself from sibling tools like 'lca_disclosure_fields' which also list fields, missing an opportunity to clarify its specific scope.

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

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

The description provides no guidance on when to use this tool versus alternatives, nor any prerequisites or context for invocation.

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 must disclose traits. It states 'Discover' but does not mention read-only nature, authentication, or side effects. It is minimally adequate but adds no behavioral context beyond the obvious.

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?

One sentence, efficient, front-loaded with the verb. Every word earns its place.

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

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

For a simple file URL discovery tool with 3 params and no output schema, the description is fairly complete. It could mention file formats, but overall it adequately informs the agent.

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

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

Schema description coverage is 100% with clear parameter descriptions. The tool description adds no extra meaning beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states the verb 'Discover' and the resource 'file URLs', specifying the programs (LCA, PERM, H-2A, H-2B, CW). It distinguishes from sibling tools like foreign_labor_search and foreign_labor_fields.

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 like foreign_labor_search or lca_disclosure_files. The description implies its purpose but does not provide when-not or alternative recommendations.

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 that the first call downloads and caches (slow), subsequent calls hit cache (fast). It also explains that certain visa programs are inappropriate for certain queries. However, it does not explicitly state if the tool is read-only or has side effects beyond caching, which is mostly 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 relatively long but well-structured. It front-loads the main purpose and routing instructions, then provides performance notes. Every sentence adds value, though it could be slightly more concise without losing 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 11 parameters and no output schema, the description covers the tool's functionality, usage guidance, performance characteristics, and parameter hints. It does not explicitly describe the output format, but mentions 'matching records' and cache format. It is fairly complete for this complexity level.

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 significant value beyond the schema. It explains the meaning of visaProgram values (agriculture, non-agriculture, etc.), warns about first-call timeout, and clarifies that maxItems=0 means no cap. This helps the agent select and invoke correctly.

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 stream-searches and normalizes DOL OFLC disclosure records across LCA, PERM, H-2A, H-2B, and CW programs. It distinguishes from siblings by specifying when to use which visa program, and explicitly warns not to use for general restaurant research, directing to places_search instead.

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

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

The description provides explicit routing instructions by visa program (e.g., 'H-2A is AGRICULTURAL seasonal labor... never use H-2B for farms'), tells when not to use (e.g., restaurants), and suggests narrowing parameters (maxItems, employerName, etc.) to avoid first-call timeouts. It also mentions that first call is slow and subsequent calls are fast.

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 must fully convey behavior. It only says 'Read field names,' omitting details about data sources, filtering effects, output format, or side effects. The 17 optional parameters suggest complex behavior not explained.

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 with no fluff. However, it could incorporate more context without significant bloat, given the tool's complexity.

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 17 optional parameters, no output schema, and no annotations, the description is inadequate. It fails to explain the relationship between parameters and the returned field names, nor the source of the XLSX file.

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

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

Schema coverage is 100%, so the schema already describes each parameter. The description adds no additional meaning beyond reading field names, failing to explain how parameters affect the output (e.g., do filters limit fields or rows?). 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 reads field names from a DOL LCA disclosure XLSX file, specifying the verb and resource. However, it does not distinguish it from sibling tools like foreign_labor_fields or whd_enforcement_fields, which also list field names for different datasets.

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

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

No guidance is provided on when to use this tool versus alternatives such as lca_disclosure_files or lca_search. The description lacks context about prerequisites or typical 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 provided, so the description must convey behavior. It implies a safe, read-only retrieval of URLs without side effects. However, it does not explicitly mention idempotence, rate limits, or authentication needs. The description is adequate but minimal.

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 sentence with no filler words. Every part adds information: verb, resource specificity, temporal scope. Efficiently structured for quick parsing.

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?

Lacks details about the return format (e.g., single URL object, list, mapping). No output schema is provided. For a tool returning multiple URL types, the agent might need to know structure to use the result. Could be more 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?

Both parameters ('quarter' and 'fiscalYear') are fully described in the schema with min/max bounds and text. The description adds no extra meaning beyond 'for a fiscal year quarter'. With 100% schema coverage, 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?

Clearly states the tool returns specific DOL LCA file URLs (disclosure, Appendix A, worksite, record-layout) for a given fiscal year quarter. The verb 'Return' is precise and the resource list differentiates it from sibling tools like 'foreign_labor_files' or 'lca_disclosure_fields'.

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

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

No guidance on when to use this tool versus alternatives. Among many sibling tools (e.g., 'foreign_labor_files', 'lca_disclosure_fields'), there is no mention of contexts where this is preferred or not. The description only states 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 provided, so the description must fully convey behavioral traits. It mentions output components but does not disclose that the tool aggregates data, is read-only, requires no special auth, or any rate limits. The fact that it 'builds a profile' suggests multiple queries, but this is not explicitly 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?

A single sentence, efficient and front-loaded with the core action. The list of output components is concise but could be slightly more structured. No unnecessary 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?

With 17 parameters, no output schema, and no annotations, the description is too brief. It does not explain how the profile is returned (e.g., aggregated statistics vs. rows), pagination, or any constraints. For a tool with many filters, more contextual detail is needed.

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

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

Schema coverage is 100%, so baseline is 3. The description adds no new meaning beyond listing output fields; parameters are already fully described in the schema. There is no mapping of parameters to the output components mentioned.

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 builds an 'employer profile' with specific aggregated data (certification counts, wage statistics, top job titles, SOC codes, worksites, flags), distinguishing it from sibling search tools that return 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?

No explicit guidance on when to use this tool versus alternatives like 'lca_search' for individual records or 'foreign_labor_search' for broader data. The description implies it is for aggregated profiling, but does not say when not to use it or list 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 are provided, so the description must fully disclose behavioral traits. It fails to mention any side effects, data freshness, rate limits, pagination behavior, or whether the data is live or cached. The description only states the search action, which is insufficient for a tool with 17 parameters.

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 of 18 words, efficiently listing the key filter dimensions without repetition or fluff. It is front-loaded with the main action and resource.

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

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

The description does not mention output format, pagination, or interpretation of results. With no output schema and 17 parameters, the description should at least hint at the nature of results (e.g., list of LCAs) or how maxResults affects output. It is incomplete 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 each parameter already has a brief description. The tool description adds no new meaning beyond grouping filter types (employer, worksite, etc.). With full schema coverage, baseline score of 3 applies.

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

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

The description clearly states the resource (official DOL OFLC LCA disclosure XLSX data) and the action (search by various filters). It enumerates multiple filter dimensions, making the tool's purpose specific and distinct from sibling tools like foreign_labor_search or lca_employer_profile.

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

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

The description implies usage by listing search filters, but it does not provide explicit guidance on when to use this tool versus alternatives (e.g., foreign_labor_search for broader LCA data). No when-not-to-use or prerequisite information is given.

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

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

No annotations are provided, and the description only states that the tool returns metadata fields. It fails to disclose behavioral details such as default dataset, pagination (e.g., limit parameter), case-insensitivity of search, or any rate limits. The description does not contradict annotations but is insufficient for an agent to understand the tool's behavior.

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

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

The description is a single, clear sentence of 13 words. It is highly concise and front-loaded with the essential purpose. Every word contributes meaning, and there is no unnecessary 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 that there is no output schema, the description should explain the structure of returned metadata fields, but it does not. It also omits default behavior for the 'dataset' parameter and how 'search' filtering works. For a tool with 3 parameters and no output schema, the description is incomplete for an agent to reliably invoke 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 for all three parameters. The description adds little beyond the schema, merely stating the return of metadata fields. It does not explain parameter interactions or provide additional context, so a baseline score of 3 is appropriate.

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

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

The description clearly states the verb 'Return' and resource 'metadata fields' for the 'official DOL OSHA inspection or violation dataset'. It effectively identifies the tool's purpose and the datasets it operates on. However, it does not explicitly distinguish from sibling tools like 'osha_inspection_search' or 'dol_datasets_search', which slightly reduces clarity.

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 such as 'osha_inspection_search' or 'osha_inspection_detail'. It implies but does not state that this tool is for exploring available fields, not for retrieving actual data. There is no mention of prerequisites or 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?

With no annotations, the description carries the full burden of behavioral disclosure. It states the core lookup and optional join but does not clarify permissions, side effects, rate limits, or whether it is read-only. The behavior is adequately implied but not explicitly detailed.

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-formed sentence with no unnecessary words. It is front-loaded 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 output schema, the description should explain what the result contains. It only says 'Look up one OSHA inspection' but does not describe the return fields or structure. For a simple lookup, this is a notable gap.

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

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

Schema coverage is 100%, and the description adds minimal value beyond the schema. The description restates the optional join but does not introduce new semantic meaning for parameters. 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 specifies a clear action ('Look up'), a precise resource ('one OSHA inspection by activity number'), and an optional behavior ('join violation/citation records'). It effectively distinguishes from sibling tools like osha_inspection_search and osha_fields.

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 provide any guidance on when to use this tool versus the many sibling tools (e.g., osha_inspection_search, osha_fields). It mentions the optional join but does not explain when to request violations or when not to join.

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 carries full burden. It discloses the optional join of non-deleted violations, but does not state whether the tool is read-only, any permission requirements, or rate limits. Partially 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, front-loaded sentence of 16 words, perfectly concise and efficient with 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 the tool's high parameter count (11) and lack of output schema or annotations, a one-sentence description is insufficient. It omits details about output format, paging, or the effect of the violation join on results.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds no extra parameter meaning beyond the schema; it only mentions the join behavior, which is not parameter-specific.

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

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

The description clearly states the verb 'Search', the resource 'official DOL OSHA inspection records', and the optional join of violation/citation records, making the purpose distinct from siblings like osha_inspection_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 provides no guidance on when to use this tool versus alternatives, such as osha_inspection_detail or osha_fields. It lacks explicit context about prerequisites or 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 provided, so description carries full burden. It states 'Static reference' implying read-only behavior and lists output fields including a caveat. Does not detail auth or rate limits, but as a lookup tool it is sufficiently transparent for an agent.

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 paragraph but packs essential information: purpose, output fields, and usage context. Could be broken into shorter sentences for easier parsing, but is not verbose and front-loads the key point.

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

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

No output schema exists, but description enumerates all return fields (jurisdiction tier, program name, etc.) and explains the use case. Lacks mention of error handling or validation of state codes, but for a simple lookup 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?

Only one parameter (stateCode) with 100% schema coverage. Schema already describes it as USPS two-letter code, case-insensitive. Description adds no extra meaning beyond schema, so 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 the tool returns specific fields (jurisdiction tier, program name, etc.) and explicitly contrasts with sibling tools like osha_inspection_search by noting it as a static reference for sparse data scenarios.

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

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

Provides explicit when-to-use guidance: 'when an agent's OSHA query in MI / MN / IA / IN / CA / WA returns sparse recent data' and explains how the lookup helps obtain fresher data. Differentiates from alternatives by being a static reference.

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 bears full burden. It mentions higher pricing tier for includeAtmosphere, but lacks details on error handling, rate limits, or side effects. The read-only nature is implied but not explicit.

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

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

Two sentences, front-loaded with core purpose, no wasted words. Efficient and clear.

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 3 parameters (all documented in schema) and no output schema, description explains return content (hours, flags, detail fields) and the optional atmosphere data. Lacks return format details but adequate for a detail lookup.

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 has 100% coverage, but description adds context for includeAtmosphere (what it fetches, pricing implications). Does not add much for dryRun beyond schema, but overall adds 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?

Description clearly states it looks up one Google place by Place ID, specifies return fields (hours, delivery/dine-in flags, detail fields), and distinguishes from places_search which would be 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?

Describes when to use (with Place ID for detailed info) and the includeAtmosphere option with pricing tier note. Does not explicitly mention when not to use, but context is sufficient.

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

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

With no annotations, the description discloses auto-paging up to maxResults, deduplication, source-tracing via googleMapsUrl, and default filters. However, it does not mention idempotency, rate limits, or authentication, which are relevant for 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 four concise sentences, front-loaded with the core function, followed by context, behavior, and defaults. 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?

Given 9 parameters and no output schema, the description covers key behaviors and defaults but does not fully describe the return structure beyond 'deduplicated results with googleMapsUrl'. It could mention pagination token handling or location bias, but overall 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%, and the description adds contextual value: explains auto-paging behavior for maxResults, defaults for includedTypes, excludeClosed, regionCode, and the cityFilter's purpose to handle spillover from Google's text search. This goes beyond basic 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 clearly states 'Search Google Places (New) Text Search for businesses in an area' and specifies it returns deduplicated results with googleMapsUrl. It distinguishes from siblings like places_detail by framing it as a retrieval primitive for the Restaurant Research Agent.

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?

While the description notes it's 'Designed as a per-round retrieval primitive for the Restaurant Research Agent', it does not explicitly contrast with sibling tools like places_detail or state when not to use it. Implied usage is present but no exclusions or alternatives 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?

With no annotations provided, the description fully bears the burden. It discloses that SAM.gov returns solicitations (not awards), awardAmount is null on most rows, and certain filters are client-side. This is thorough behavioral 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 front-loaded with purpose, lists key filters, notes limitations, and ends with an alternative. Every sentence is essential; no redundancy or fluff.

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

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

Given 11 parameters, 100% schema coverage, no output schema, the description fully explains the tool's behavior, limitations, and when not to use it. It is 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?

Schema coverage is 100%, so baseline is 3. The description adds significant meaning: e.g., 'state' is deprecated; 'dryRun' defaults true when no key; 'officeState' filters by contracting office not POP; 'placeOfPerformanceCity' and 'placeOfPerformanceState' are client-side. This exceeds expectations.

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

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

The description states it searches 'SAM.gov Opportunities API by title keywords, NAICS codes, procurement type, set-aside, contracting office state, and posted date range.' It clearly distinguishes from sibling tools like sam_opportunity_detail (detail) and usaspending_award_search (awarded contracts).

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

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

Provides explicit guidance: 'For awarded federal contracts with dollar amounts, use USAspending.gov instead.' Also notes that place-of-performance filters are applied client-side due to API limitations, helping the agent know when this tool is appropriate.

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

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

No annotations provided, so description carries full burden. It discloses the need for an API key in live mode and the dryRun parameter for sample data. However, it does not mention rate limits, error handling, or response behavior, which are gaps in 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?

Two sentences, front-loaded with purpose, no extraneous information. Every sentence adds value. Highly 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 tool's simplicity (2 params, no output schema, no annotations), the description adequately covers purpose, key parameter, and a precondition. Could expand on expected response or error scenarios, but is sufficient for a basic lookup tool.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds no additional meaning beyond what the schema provides. The schema already clearly describes noticeId and dryRun. The description reinforces the purpose but doesn't enhance parameter understanding.

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 one SAM.gov opportunity by notice ID, using a specific verb and resource. It clearly distinguishes from sibling tools like sam_opportunities_search, which searches multiple opportunities.

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 indicates usage context: for a single opportunity by notice ID, and notes that live mode requires an API key. While it doesn't explicitly exclude alternatives, the context is clear. Could be improved by stating when not to use (e.g., for bulk search).

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

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

With no annotations, the description carries the full burden. It states the tool returns codes, implying a read-only operation. However, it lacks details on whether the list is static or dynamic, how often updated, or any other traits. Adequate but not transparent beyond the basic action.

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 immediately states the action and output. Front-loaded and efficient, with zero filler.

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

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

Given the tool's simplicity (no parameters, no output schema), the description is largely complete. It identifies the resource type and relationship to a sibling tool. However, it does not describe the return format (e.g., list of strings), which would help an agent fully utilize the 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?

There are zero parameters, and schema coverage is 100% (empty). The description adds value by specifying the kind of codes (procurement type and set-aside), which is beyond the schema. Baseline for 0 params is 4, and the description meets it.

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 specifies 'Return common SAM.gov procurement type and set-aside codes' and clarifies their use in the opportunity search tool, distinguishing this tool from siblings like sam_opportunities_search (which returns opportunities, not codes). This provides a clear, specific purpose.

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 codes are 'used by the opportunity search tool', implying a preparatory role, but does not explicitly state when to use or when to avoid it. No alternatives or exclusions are provided, limiting 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 the full burden. It discloses that the data is a static reference, notes which states are verified (10 Midwest) and which need sanity-checking (40 others), and mentions bulk-download availability. This provides good transparency about data quality and limitations.

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 key information front-loaded. It is efficient and contains no filler, though one could argue the bulk-download mention could be integrated more tightly. Still very 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 tool's complexity (static reference for 50 states with varying verification), the description covers the return values, use cases, data caveats, and sibling tool pointer. It is complete enough for an agent to understand scope and limitations.

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 already describes the stateCode parameter (USPS code, length, case-insensitivity). The description adds no additional semantic value 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's purpose: it returns the URL and agency for a US state's business-entity search portal. It uses specific verbs and resources, and distinguishes itself from the sibling tool 'business_entity_search' by noting the latter is for programmatic lookups.

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

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

Explicitly provides when to use (manual verification, records requests, state search forms) and when not to use (prefer programmatic lookups via OpenCorporates). Also mentions bulk-download availability for specific contexts.

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 effectively communicates that the tool searches for awards with known dollar amounts, defaults to contract types and a recent time range, and supports various filters. It does not detail pagination or rate limits, but the parameter descriptions in the schema cover many behavioral aspects. No contradictions are present.

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

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

The description is concise at three sentences, with the first sentence establishing purpose, the second providing usage guidance, and the third summarizing filters and defaults. It is front-loaded and 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 the complexity of 19 parameters and no output schema, the description adequately covers the tool's scope, default behavior, and filter capabilities. It does not describe return format, but the core functionality is clearly communicated, making it nearly complete for this type of 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 coverage is 100%, so the baseline is 3. The description provides a high-level summary of filter categories (NAICS, PSC, recipient, etc.) but does not add new meaning beyond what the parameter descriptions already offer. It reinforces the schema without adding semantic value.

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

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

The description clearly states the tool's purpose: searching USAspending.gov for federal awards with known obligated dollar amounts. It distinguishes from the sibling tool 'sam_opportunities_search' by noting that SAM.gov returns solicitations, not awards, making the purpose and differentiation explicit.

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 when-to-use guidance with example user queries ('how much was contract X for', 'all federal contracts in Y over $Z') and contrasts with SAM.gov. It also mentions that no API key is required and states default behaviors (contract award types, past 12 months), offering clear context for tool 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. Description only implies a read operation but does not disclose any behavioral details such as error handling, response format, or permissions.

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?

One concise sentence with no fluff, front-loaded.

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

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

Given the absence of output schema and annotations, the description is minimal but sufficient for a simple lookup; it does not mention the optional fields parameter or describe the return structure.

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

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

Schema coverage is 100%, so description adds no extra meaning beyond the schema; the fields parameter is not mentioned.

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 looks up WHD Enforcement records by numeric case_id, but lacks differentiation from sibling tools like whd_enforcement_query or whd_enforcement_metadata.

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

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

No guidance on when to use this tool vs alternatives; no exclusions or context 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 present, so the description must carry the full burden. It only states 'return concise...' without disclosing whether this is a read-only operation, any rate limits, or the format of the response. The behavioral traits are essentially absent.

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 conveys the core purpose without any extraneous words. Perfectly concise and front-loaded.

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

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

Given low complexity (3 optional parameters) and no output schema, the description is adequate but could be improved. It does not mention the structure of returned data or what categories are available, which would help an agent interpret results.

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

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

Schema coverage is 100% with each parameter having a description. The description adds no additional meaning beyond the schema (e.g., 'case-insensitive' is already in 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 returns field metadata (names, labels, descriptions, categories, data types, units) for WHD Enforcement. This distinguishes it from sibling tools like whd_enforcement_case (case data) and whd_enforcement_query (querying 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?

No guidance is provided on when to use this tool over siblings such as whd_enforcement_metadata or other field-listing tools. The agent has no context to decide if this is the appropriate tool for discovering available fields.

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 does not state that the tool is read-only, safe, or any behavioral traits. The description adds no transparency beyond the basic 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, clear sentence with no extraneous words. Every part contributes to the purpose.

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

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

For a tool with simple parameters and no output schema, the description is minimally adequate but lacks usage guidelines and behavioral information, leaving gaps for an agent to fully understand when and how to invoke the tool.

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

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

Schema description coverage is 100%, so each parameter is already documented. The description adds no additional meaning about parameters beyond 'optionally filtered by text', which is already implied by the search parameter 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 the verb 'return' and the resource 'metadata rows for the WHD Enforcement dataset'. It mentions optional filtering but does not explicitly differentiate from sibling tools like whd_enforcement_fields or whd_enforcement_case, which likely return different data types.

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

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

The description provides no guidance on when to use this tool versus alternatives. It mentions optional filtering but does not specify context such as use cases, prerequisites, or exclusions.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It reveals critical behavioral traits: that findings_end_date is the violation end date (not case conclusion), typical investigation lag (6-24 months), and that ld_dt is a load date. This goes beyond basic read-only hints and helps the agent avoid semantic errors, though it could mention pagination or default limits.

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 paragraph that front-loads the purpose and then provides essential usage warnings. Every sentence adds value. It could be slightly more concise or broken into bullet points, but it remains efficient and clear.

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

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

Despite lacking an output schema, the description is fairly complete given the tool's complexity. It details crucial date semantics and suggests query strategies. It does not list all possible return fields, but a sibling tool (whd_enforcement_fields) likely covers that. The description adequately prepares the agent for correct invocation.

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

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

Schema coverage is 100% with all parameters having descriptions, so the baseline is 3. The description adds valuable context about the data fields (findings_end_date, ld_dt) but does not enhance parameter semantics beyond what the schema provides. The warnings are complementary rather than parameter-specific.

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 'Query' and identifies the exact resource: 'concluded Wage and Hour Division compliance actions from the DOL WHD Enforcement (WHISARD) dataset.' It clearly distinguishes from sibling tools like whd_enforcement_case (single case detail) and whd_enforcement_fields (metadata) by focusing on querying a dataset. The important date semantics add further clarification.

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 guidance on when to use this tool correctly, especially regarding date filtering: it warns that findings_end_date is not the case conclusion date and advises using a wider window when filtering for recent cases. It does not explicitly state when not to use it or name alternative tools, but the context is clear enough to prevent common misuse.

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