grant-finder

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

No annotations are provided, so the description carries full burden. It describes the output but does not disclose behavioral traits such as read-only nature, data freshness, latency, or side effects. The description assumes a safe read operation but does not confirm 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?

The main sentence is concise and front-loaded with the core purpose. However, the cryptic phrase 'The reminder annuity's data spine' is confusing and adds no value, slightly detracting from clarity. Overall, it is mostly efficient with minor excess.

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 two numeric inputs and no output schema, the description explains inputs and output format (deadlines with cites and administering body). However, it lacks details such as which benefits are considered, how many deadlines are returned, or whether results are ordered. It is adequate but not fully complete.

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

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

Schema description coverage is 0%, so the description must compensate. It vaguely references 'household situation' but does not explain the exact meaning of 'householdIncome' (e.g., annual/monthly, gross/net) or 'householdSize' (number of people). The description adds minimal semantic value beyond the parameter names.

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

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

The description clearly specifies the tool's purpose: given a household situation, it returns application/recertification/reporting deadlines with CFR/statute cites and administering body. The verb 'return' and resource 'deadlines' are explicit, and the scope is distinct from sibling tools like 'qualify_check' (which likely checks eligibility, not deadlines).

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 input condition ('Given a household situation') but provides no explicit guidance on when to use this tool versus alternatives or when not to use it. Usage context is implied by the description but lacks exclusions or comparisons with 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 provided, the description carries the full burden of behavioral disclosure. It mentions the tool is free and that it hands off to the hospital's office, which provides some transparency. However, it does not disclose whether the tool makes external calls, modifies data, or has any side effects, leaving gaps in understanding 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 three sentences long, with the first sentence stating the main purpose, the second emphasizing the free nature, and the third describing the hand-off. It is efficient and front-loaded with critical information, though it could be slightly more compact.

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 7 parameters, no output schema, and no annotations, the description lacks detail on return values, eligibility thresholds, or what 'likely eligibility' means. While it explains the core FPL comparison, it omits important context about how other parameters influence the result, leaving the tool incomplete for an 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?

The description adds context beyond the schema by explaining the core logic (income vs. FPL) and referencing state laws and the No Surprises Act. However, it does not detail individual parameters like 'billExceedsEstimate' or 'wasEmergency'. Given 0% schema description coverage, the description compensates moderately but could be more 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 tool detects eligibility for nonprofit hospital charity care, financial assistance, and the No Surprises Act based on income vs. FPL. It uses a specific verb ('detect') and resource ('eligibility'), and distinguishes itself from sibling tools like 'qualify_check' or 'visa_match' by its healthcare focus.

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 explicit guidance on when to use this tool versus alternatives. It implies usage for charity care eligibility checks but offers no comparisons or exclusions relative to sibling tools such as 'applyby_deadlines' or 'life_event_scan'.

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 clarifies the tool does not grant citizenship, but does not disclose technical behavior, such as data sources or offline/online operations. Adds context about limitations, but lacks depth.

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 deliver key info: purpose, scope, and limitations. Could be better structured (e.g., bullet list of countries) but is clear and 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?

Description mentions output is information and checklist, but lacks specifics on return format or structure. For a tool with 8 parameters and no output schema, more guidance on what the agent receives 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 50%; descriptions for some parameters (e.g., 'ancestorNaturalizedYear') exist in schema but tool description adds no extra meaning. Parameters like 'ancestorEmigratedYear' lack schema description and tool description ignores them. Fails to compensate for gaps.

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 'detect eligibility' and resource 'second citizenship by ancestry', specifying four countries and informational role. It distinguishes from siblings by emphasizing it is an information/checklist tool, not a recognition 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?

Explicitly says 'INFORMATION + DOCUMENT-CHECKLIST ONLY' and that recognition is decided by foreign government, indicating when to use (for info) and when not (for actual application). Does not mention sibling tools explicitly but sets clear boundaries.

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 that the tool is pay-per-call via x402 (USDC on Base), which is a key behavioral trait. It also mentions 'rule-cited with authority hand-off'. However, no annotations exist, so the description partly fills the gap. It does not disclose any side effects, rate limits, or required permissions for a premium service.

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 sentence containing multiple clauses and concepts. While it packs information, it lacks structure (e.g., bullet points, separate sections). It is functional but not optimally concise or scannable for an AI agent.

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

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

The tool has moderate complexity (3 parameters, multiple outputs implied) and no output schema. The description mentions components (comps, insurance gap, grading call) but does not explain the output format, how results are returned, or how to interpret the appraisal. This leaves the agent with incomplete context to correctly handle the response.

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 only 33% (only perItemSpecialLimit has a description). The tool description does not explain what the required 'query' parameter or the optional 'niche' enum represent. Given low coverage, the description fails to add meaning beyond the schema. The 'perItemSpecialLimit' description is present but the overall parameter semantics are underinformed.

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 specifies a premium appraisal tool that provides live valuation, insurance gap analysis, grading worth-it call, and rule citations. It indicates the resource (GrailQualify appraisal) and actionable outputs. However, the title is null and the description lacks a distinct verb (e.g., 'returns', 'generates'), and it does not differentiate from the sibling 'grail_value' tool, which may offer a simpler service.

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. Despite having siblings like 'grail_value' and 'qualify_check', the description does not mention any context, prerequisites, or exclusion criteria. The 'PREMIUM' label hints at cost but does not help in decision-making between 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 the burden. It discloses the output includes a confidence-tiered estimate with comp shops and scrape date, and implies it is a read operation. However, it lacks details on auth requirements, rate limits, or 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?

The description is two sentences, front-loaded with purpose, and contains 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 tool has 2 simple parameters and no output schema, the description adequately describes the output (confidence-tiered estimate with comp shops and scrape date) and distinguishes from the sibling. However, it omits guidance on optional parameters and error handling.

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 50% (only 'query' has a description). The description does not explain the 'niche' parameter or its enum values, nor does it elaborate on how parameters affect behavior. It adds only general context about valuation but not parameter specifics.

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 'Value a collector's item' using live retail and sold comps, returning a confidence-tiered estimate. It distinguishes from sibling 'grail_appraise' which is the premium 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?

It explicitly mentions 'Free preview' and contrasts with the premium tool 'grail_appraise', guiding when to use each. However, it does not explicitly list scenarios where this tool should not be used.

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 explains the tool is information + enrollment-nudge only, the plan administrator decides, and it is employer-pays B2B2C. This fully discloses the non-action-taking, consultative behavior.

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

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

Three sentences that front-load purpose and add context. Every sentence adds value, though the first sentence is somewhat long. Appropriately sized for 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?

No output schema, and description does not detail return format. With 10 parameters and a detection task, more details on what 'detect' outputs would improve completeness. However, the description covers core behavior and constraints adequately.

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 0%, but description lists some benefit types that map to parameters (e.g., dependent-care FSA, HSA match). It adds meaning beyond boolean names, but not all 10 parameters are explicitly covered (e.g., hasHdhp, dependentsUnder13 are implied). Partial compensation.

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 detects under-used employer benefits an employee qualifies for, listing specific benefit types (dependent-care FSA, student-loan repayment, fertility/IVF, HSA match). This distinguishes it from sibling tools like life_event_scan or missed_credits_scan.

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 indicates the tool is informational and nudge-only, handing off to HR/SPD. It specifies ERISA-aware and non-medical scope. However, it does not explicitly state when not to use or name alternatives, though 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?

No annotations are provided, so the description carries full burden. It clearly discloses the premium/pay-per-call model via USDC on Base and the behavior of returning all findings at once with rule citations. It does not mention destructive actions, which is appropriate for a scan 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 concise, fitting in one dense sentence. It front-loads the 'PREMIUM' label and key mechanic. However, it could be slightly more structured for readability.

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 9 parameters, no annotations, and no output schema, the description is insufficient. It lacks details on parameter usage, output format, and edge cases, making it hard for an agent to invoke correctly without additional knowledge.

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

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

Schema description coverage is 0%, meaning no parameter descriptions in the schema. The tool description does not explain the meaning of parameters like householdIncome, householdSize, creditScore, etc. It only mentions the event trigger, leaving 8 other parameters undocumented. This is a critical gap.

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: scanning all relevant spine verticals triggered by a life event, returning comprehensive findings with citations. It distinguishes itself from sibling tools like missed_credits_scan or hr_benefit_scan by covering multiple verticals simultaneously.

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 life-event-driven comprehensive scans but does not explicitly state when to use versus alternative individual scan tools. It provides context about the reversal mechanic but lacks clear when-not or alternative 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 are present, so the description carries the full burden. It honestly discloses that the tool only detects and explains, never files, and mentions confidence tiers and IRS citations. This provides sufficient insight into behavior for a read-only scanning 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 a single, dense sentence that front-loads the main purpose and packs detailed information. While clear, it could be broken into two sentences for easier parsing, but overall it is efficient and not 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 14 parameters and no output schema, the description lacks detail on the output format (e.g., how credits are listed, confidence levels) and how parameters are used. The mention of 'confidence-tiered' and 'hand-off' provides some context, but not enough for a complex 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 only 14% schema description coverage (2 of 14 parameters described), the description should compensate but does not add meaning for most parameters. It names credits but does not explain how each parameter (e.g., energySpend, childcareCost) maps to detection logic, leaving ambiguity.

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 the exact action: detecting federal tax credits a household likely qualifies for but commonly never claims. It lists specific credits with IRS citations and explicitly distinguishes from filing a return, making the purpose crystal clear.

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 using the tool (detecting unclaimed credits) and explicitly states it never files a return, which guides appropriate use. However, it does not directly compare to sibling tools or specify when not to use it, so a slight deduction applies.

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 key traits: returns confidence tiers (LIKELY/VERIFY/UNLIKELY), cites governing rules, provides verify-date and administering body, and clarifies it does not file or guarantee results. However, it does not discuss data handling or privacy implications.

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 concise at three sentences, starting with a clear label 'Eligibility-navigator' and immediately stating the input-output relationship. The final disclaimer is slightly redundant but does not hinder 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 complexity and lack of output schema, the description adequately explains the output format (benefits with confidence tier, rule, verify-date, administering body). It does not detail how to interpret confidence levels or handle state-specific rules, but covers essential behavioral aspects.

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 83%, so baseline is 3. The description adds marginal value by listing key parameters (income, size, filing status) but does not elaborate on optional parameters like retirementContribution or hasAffordableEmployerCoverage 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 defines the tool as an eligibility navigator that returns benefits and credits a person may qualify for, with confidence tiers and detailed citations. It distinguishes itself from siblings like 'missed_credits_scan' by focusing on eligibility for federal/state benefits rather than scanning for missed credits.

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 (given household situation) but lacks explicit guidance on when not to use it or alternatives among the sibling tools. The disclaimer 'never a guarantee; never files for you' provides some usage boundary but does not direct to other tools for specific scenarios.

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 transparency burden. It states the tool is for viability detection only, not filing, and that it hands off to CPA/program office. However, it does not disclose any behavioral traits like what happens after screening (e.g., returns a boolean or report), authentication needs, or whether it 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 a single sentence that packs essential information about what grants are screened and the non-filing nature. It is front-loaded and free of fluff, though a slightly structured format (e.g., listing grant types) could improve scannability.

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 13 parameters, no output schema, and no annotations, the description is critically incomplete. It does not explain what the tool returns, how to interpret results, or how individual parameters (e.g., 'state', 'preRevenue', 'grossReceiptsThisYear') affect the screening outcome.

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 13 parameters with 0% description coverage, yet the description mentions none of them by name or role. It vaguely refers to 'activities' but provides no mapping to parameters like 'activityTechnical', 'facedTechnicalUncertainty', or 'grossReceiptsThisYear', leaving the agent without guidance on how to populate 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 screens eligibility for the federal R&D tax credit (26 U.S.C. 41 4-part test), payroll-tax offset, and SBIR/STTR + state grants. It distinguishes itself from filing services by explicitly noting 'VIABILITY DETECTION ONLY' and that it never takes a percentage, which clarifies its role and differentiates it from sibling tools like 'qualify_check' or 'life_event_scan'.

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 eligibility screening of R&D credits and grants, and clarifies it is not a filing service. However, it does not provide explicit when-to-use or when-not-to-use guidance, nor does it compare with sibling tools or specify prerequisites (e.g., requiring a CPA partner).

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 B2B nature, RESPA compliance, flat-fee pricing, and no kickbacks, which is helpful. However, it lacks details on error handling, data retention, or permissions required, so transparency is incomplete.

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 purpose, compliance, and output order. It is front-loaded and no filler, though slightly 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?

The description lacks detail on output format (e.g., just program names or full details) and does not specify input constraints (e.g., valid state values, income limits). With no output schema and many parameters, the description is insufficient for complete understanding.

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 0%, but the description does not explain individual parameters beyond mentioning 'buyer's 8 fields'. It fails to add meaning to fields like creditScore range, householdIncome constraints, or propertyType implications.

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: given buyer's fields, it returns loan programs the buyer likely passes, sequenced in apply-order. It distinguishes from siblings by specifying it's for loan program qualification (as opposed to visa match or charity care 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 description indicates when to use (given buyer's fields) and mentions the tool is RESPA-safe and flat-fee, implying appropriate contexts. However, it does not explicitly state when not to use or suggest alternatives 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 provided, the description carries the full burden. It discloses that the tool provides information only, defers to attorneys, and never files a petition. This transparently sets expectations about its non-actionable nature, though it lacks details on data handling or error behavior.

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

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

The description is concise, consisting of two sentences that front-load the core functionality and end with critical disclaimers. Every word serves a purpose, with no filler.

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

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

The description mentions that output includes 'governing statute cited and a confidence tier,' which partially addresses expectations. However, no output schema is provided, and for a tool with 12 parameters, more detail on the output structure would enhance 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 schema has 12 parameters with only 25% description coverage. The description does not elaborate on parameter meanings beyond the schema. It does not add significant context for the majority of parameters, leaving the agent to rely solely on the schema's minimal descriptions.

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

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

The description clearly states the tool's purpose: to detect which U.S. visa categories likely fit a person's situation, listing specific categories like O-1, EB-2 NIW, etc. It is distinct from sibling tools, which are unrelated to visa matching.

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 the tool (for visa eligibility assessment) and includes important caveats (information only, not legal advice, never files a petition). However, it does not explicitly compare to alternatives among siblings, but no sibling offers similar functionality.

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