Untax

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

With no annotations, the description carries full disclosure burden. It adds real value by citing the 40% median surge rule under T.C.A. § 67-5-1701, which grounds the computation legally. But it says nothing about the return value, what happens for unsupported counties, or whether the result is a flag versus a computed percentage.

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 dense sentence that front-loads the core operation and puts the key legal threshold inline. 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?

For a 3-param computation tool with a fully documented schema, the description covers the essential purpose and threshold. With no output schema, it could say more about what result is produced (e.g. surge percentage, pass/fail flag), which keeps it from a 5.

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

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

Schema description coverage is 100%, so the baseline is 3. The description contextualizes the county parameter via the statute-specific benchmark and the Hamilton/Knox scope, but adds no syntax or format detail beyond the schema's own prior/current value descriptions.

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

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

States a specific verb (evaluate), resource (individual parcel appraisal surge), and scope (between reappraisal cycles against county benchmarks). The 'individual parcel' framing implicitly contrasts with county/roll-level analytics siblings like get_hamilton_roll_analytics, but no sibling is named explicitly.

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

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

The phrase 'evaluate an individual parcel's appraisal surge' implies when to reach for this tool, and the benchmark context clarifies the use case. However, there is no explicit when-not guidance, no prerequisites, and no named alternatives for portfolio- or roll-level comparisons.

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 behavioral burden, yet it doesn't say whether this is a read-only calculation or a filed audit, whether results depend on eligibility screening, what happens if the member fails a threshold, or what the response contains. 'Audit and calculate' signals an eligibility determination plus a dollar computation, but nothing about permissions, side effects, or determinism is disclosed.

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 dense sentence with the operative verb and scope front-loaded; the statute and form citation earn their place by anchoring the legal basis. 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?

A 10-parameter, legally specialized tool with no annotations and no output schema needs more than a statute citation. The description never states eligibility criteria, how days-deployed interacts with the tax amount to produce a result, or what the return value looks like — an agent cannot tell whether it receives an eligibility finding, a computed abatement amount, or a filing packet.

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

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

Schema description coverage is 100%, so all 10 parameters are already documented in the schema. The description adds only the statutory context for the calculation and no syntax, format, or interaction guidance beyond that, which is the expected baseline when the schema does the heavy lifting.

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

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

Specific verb pair ('Audit and calculate') paired with a precisely scoped resource: ad valorem tax abatement for active-duty members deployed outside the US under Fla. Stat. § 196.173. The statute, form number (DR-501M), and 'combat deployment' framing implicitly separate it from the broader veteran-relief siblings, though no sibling is named.

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 statutory scope implies when the tool applies (deployed service member, Florida or reciprocal state, ad valorem tax), but there is no explicit when-to-use/when-not statement and no routing to alternatives such as check_veteran_relief or audit_disabled_veteran_relief. The agent must infer the boundary from the legal citation alone.

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

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

With no annotations, the description must carry the behavioral burden. It discloses that the tool computes annual tax reduction and a 3-year retroactive refund demand, but it does not clarify whether the operation is read-only, what side effects or permissions are involved, or whether a demand letter is generated.

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, but it is front-loaded with the action and every clause contributes statutory or calculation context. It is appropriately sized for a complex legal-audit tool, though the sentence is somewhat heavy.

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

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

There is no output schema and no annotations, so the description should do more to explain what the audit returns beyond the high-level annual reduction and refund demand. It provides enough to understand the purpose but leaves return structure and eligibility nuances underspecified.

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

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

Schema description coverage is 100%, so the input schema already documents all six parameters. The description adds useful legal and ratio context but does not add parameter-specific semantics beyond what the schema provides.

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

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

The description names a specific verb and resource: auditing property misclassification from 40% Commercial to 25% Residential under a cited statute, and it adds the calculation/refund scope. This is clearly distinguishable from generic sibling tools like audit_property_tax, though it does not explicitly name alternatives.

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 commercial-to-residential misclassification scenario implies when the tool applies, but there is no explicit when-to-use guidance, no exclusions, and no routing to related siblings such as audit_retroactive_tax_recovery or audit_property_tax.

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 does carry useful behavioral context: a $0.00 mandatory recording fee and statutory confidential-seal protections under T.C.A. § 10-7-513. However, it never states whether the tool merely produces a formatted slip or actually files/records something, nor what the legal exposure or side effects are – a significant omission for a document-submission 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?

A single dense sentence with no filler; the resource and the legal/fee framing are front-loaded. It is somewhat overstuffed with statutory citations, but nothing is redundant.

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 7-parameter tool with no annotations and no output schema, the description leaves the core question unanswered: what does the caller get back (a formatted slip? a filing receipt?) and does invoking it constitute a filing. Those gaps matter materially for correct invocation.

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

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

Schema description coverage is 100%, so all seven parameters are already documented in the schema; baseline 3 applies. The description adds only oblique context – the 'confidential seal protections' phrase hints at the is_sealed_from_public_inspection_requested flag, but it adds no format or validation detail 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?

Names a specific verb pair (audit and format) and a concrete resource (County Register of Deeds military discharge recording submission slip), which is far more specific than the generic 'audit_*' siblings. It is distinguishable from neighbors such as generate_veteran_packet or audit_va_award_document_with_jev, though it never explicitly says so.

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

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

There is no statement of when to choose this tool over the many adjacent veteran/recording tools (generate_veteran_packet, parse_va_benefit_letter, audit_va_award_document_with_jev). No prerequisites, no exclusions, no workflow position are given – the agent must infer usage from the name alone.

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

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

With no annotations, the description carries the full behavioral burden. 'Screen eligibility' and 'Calculates exact tax relief' imply a read-only screening/calculation operation, and the statutory caps and income threshold add useful domain behavior, but the description does not explicitly state that no records are modified, whether authorization is needed, or what happens when the homeowner is ineligible.

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 dense sentences with no wasted language. The statutory basis, eligibility scope, calculation cap, and income limit are front-loaded and easy to parse.

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

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

There is no output schema and no annotations, so the description must carry more context. It adequately describes the screening purpose and calculation limits, but it does not explain the return value format, what an ineligible result looks like, or how the required disability award and primary residence criteria affect the 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?

Schema description coverage is 100%, so the schema already documents all seven parameters. The description adds relevant context by stating the $30,000 market value cap ($7,500 assessed) and the $33,460 income threshold, but it does not map these to specific parameters or clarify the required disability award and primary residence fields beyond what the schema already says.

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

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

The description states a specific verb ('Screen eligibility') and a specific resource ('Tennessee Disabled Homeowner Property Tax Relief') with a statutory citation, which is much more precise than a generic audit tool. It implicitly distinguishes from veteran relief by naming 'disabled homeowner,' but it does not explicitly name or contrast with sibling tools such as audit_disabled_veteran_relief or check_eligibility.

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 eligibility criteria (totally disabled homeowners, household income under $33,460) imply when the tool applies, but there is no explicit guidance on when to use this versus alternatives like check_eligibility or audit_disabled_veteran_relief. No when-not-to-use conditions or routing instructions are provided.

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

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds valuable scope constraints: no default jurisdiction, no eligibility decision, no tax estimate, no generated form, and no filing. It does not describe return data or missing-fact reporting format, but with annotations covering safety the added behavioral context is solid.

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-loads the core screening purpose, and efficiently packs scope exclusions into a short clause. The internal 'compatibility alias' framing is slightly opaque but does not bloat the definition.

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 is adequate for a safe read-only screening tool with rich schema coverage and annotations. However, with 17 optional parameters and no output schema, it does not explain what the screening returns or how missing facts are reported, leaving a meaningful gap for an agent invoking it.

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

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

Schema description coverage is 100%, so the 17 parameters are already well documented in the input schema. The description categorizes the reviewed information into applicant, property, residence, review-year, and VA-related facts, but adds no syntax, format, or conflict-handling details beyond what the schema provides.

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

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

The description states a specific screening purpose: reviewing missing applicant, property, residence, review-year, and VA-related information before a program requirements review. It also distinguishes the tool from eligibility-decision, tax-estimate, form-generation, and filing tools. However, the phrase 'compatibility alias for the shared Veteran supplied-fact screening' is somewhat internal and does not explicitly name the closest sibling alternative.

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 before a program requirements review, giving some contextual timing. But it provides no explicit when-not-to-use guidance and does not name alternatives among the many veteran-relief tools in the sibling list, leaving routing inference to the agent.

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

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

No annotations are provided, so the description carries the full burden: it does not say whether this files or submits anything, whether a voucher is returned or persisted, what happens when the veteran fails the eligibility audit, or what permissions/documents are required. 'Format ... Voucher' hints at document generation but the side effects are unclear for what appears to be an eligibility-checking plus document-producing 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?

A single dense sentence with the verb and resource front-loaded and no filler. It is compact given the very long official program name, though the statutory tail slightly delays the key scope information for an agent scanning quickly.

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

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

For a six-parameter tool with no annotations and no output schema, the description omits important context: what the voucher output looks like, how eligibility failure is reported, and how the P&T / mobility-impaired condition gates the result. Adequate but with clear gaps for a document-generating compliance 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 all six parameters (including the P&T flag and VA percentage) are already documented in the schema. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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

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

The description uses a specific compound verb phrase (audit eligibility and format voucher) tied to a named resource (Disabled Veteran Motor Vehicle Registration and Wheel Tax Exemption Voucher) and cites the governing statute T.C.A. § 55-4-237. This distinguishes it reasonably from generic siblings like audit_disabled_veteran_relief, but it does not explicitly contrast itself with the closest neighbors (verify_va_disability_exemption, audit_surviving_spouse_vet_relief), which would earn a 5.

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

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

The description states the statutory basis and the qualifying population but gives no when-to-use/when-not guidance and names no alternatives among the many veteran-related siblings. An agent must infer that this handles the vehicle registration/wheel tax pathway rather than the homestead or spouse pathways.

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

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

No annotations are provided, so the description carries the full behavioral burden. 'Audit' and the detection/calculation language imply a non-mutating analysis, but the description does not explicitly state read-only behavior, permissions, data-source limitations, or error cases.

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 front-loaded sentence delivers the purpose and output scope without filler. It is dense but appropriately sized for the complexity, though splitting the calculation clause from the lookup clause could improve scanability.

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 is rich about what the audit detects and calculates, and the schema fully covers parameters. However, with no annotations and no output schema, it omits behavioral details such as return structure, data freshness, and failure modes that an agent would need for fully confident invocation.

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

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

Schema description coverage is 100%, so the schema already documents parcel_id, address, lat, lon, county, and format. The description does not add parameter-level meaning beyond what the schema provides, making the baseline 3 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?

States a specific verb and resource: 'Audit a property against the FEMA National Flood Hazard Layer (NFHL)'. It then names the exact flood-zone, FIRM, BFE, insurance, and appraisal-deduction outputs, clearly distinguishing it from the many other audit_* siblings.

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

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

The domain context implies when the tool is relevant, but there is no explicit when-to-use or when-not-to-use guidance and no named alternative among sibling tools. An agent can infer its purpose but must decide selection from the name and description alone.

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

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the description adds value by detailing what is NOT performed (no fee quote, no payment inspection, no charge, no packet generation, no submission) and by noting sandbox checkout requires separate authenticated tools. It doesn't cover rate limits or how evidence requirements are formatted, but it meaningfully extends the annotations.

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

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

Three dense, front-loaded sentences: purpose first, then the negative scope list, then the sandbox pointer. No filler, though the phrase 'service capabilities' is a bit abstract for a research tool.

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

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

There is no output schema, so the description's note that it returns 'source observations and service capabilities' carries return-value information, and the negatives define the boundary well. It could say more about evidence-requirement structure, but for a research-style tool with fully documented params this is largely complete.

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

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

Schema description coverage is 100%, so all four parameters are already documented, including the county adapter key and the enumerated service types. The description only restates the framing ('explicitly selected property', 'requested service') without adding syntax or validation nuance 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 states a specific action and scope: research an explicitly selected property and identify evidence requirements for a requested property-record service. It distinguishes this from the sandbox checkout path (start_tax_sandbox/complete_tax_sandbox_order) by naming that alternative, though the boundary with get_microtransactions_catalog remains implicit.

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 clearly frames usage: research an already-selected property, not a discovery step, and it names the exclusions (no savings, no fee quoting, no charging, no filing, no correction) plus the alternative route for checkout. It stops short of saying which of the many sibling audit_* tools to prefer, but the context is clear and the exclusions are useful.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the four-city coverage and statutory basis, but does not explicitly state that the operation is read-only, what permissions or limitations apply, or what the audit returns beyond a general reference to Exhibit P.

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 with no wasted preamble. It is dense with several clauses and legal citations, but each clause contributes to scope or expected findings.

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 is adequate for tool selection and states the audit scope and legal issues, but with no annotations and no output schema it does not fully describe operational constraints, permissions, or the structure of returned audit findings.

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

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

Schema description coverage is 100%, so the schema already documents parcel_id, address, jurisdiction, county, format, and assessed_improvement_value. The description adds little parameter-level meaning beyond the schema and mainly restates the permit-audit context.

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, "Audit," and a precise resource, municipal building/renovation/demolition permit records, with named cities and concrete audit targets. This clearly distinguishes it from sibling audit_* tools focused on tax relief, storm swaths, blight, and other parcel issues.

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

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

The description gives a clear use case: identify premature lien-date additions, demolished structures still on CAMA rolls, and maintenance protections under T.C.A. § 67-5-601/603. It does not explicitly state when not to use this tool or name a preferred alternative among the many other audit_* siblings, so usage guidance is clear but incomplete.

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 identifies the authoritative NOAA data source and statutory report output, but does not disclose whether the operation is read-only, what permissions are required, whether it writes files or records, or other side-effect details.

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

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

The description is a single, front-loaded sentence that identifies the action, data source, covered storm types, statutory use, and output artifacts without filler. Every phrase contributes to distinguishing the tool's 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?

The description names the generated deductions and certified Exhibit S reports, but with no output schema and no annotations, it does not fully explain return values, operational behavior, or when this tool should be preferred over related audit siblings. The schema covers inputs well, but contextual gaps remain for a complex statutory and weather-analysis tool.

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

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

Schema description coverage is 100%, so the input schema already explains all five parameters, including county, format, address, parcel_id, and assessed_improvement_value. The description does not add meaningful semantics beyond the schema for any parameter.

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

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

The description states a specific verb and resource: auditing a parcel against authoritative NOAA severe weather storm swaths, including hail, tornado, hurricane wind, and flash flood. It also names the statutory purpose and output artifacts, which distinguishes it from sibling audit tools such as FEMA flood hazard or general property tax audits.

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 intended use is implied by the purpose: generating statutory casualty loss assessment deductions and certified Exhibit S reports under T.C.A. § 67-5-603. However, the description does not explicitly state when to use this tool versus related siblings such as audit_fema_flood_hazard, nor does it provide exclusions or prerequisites.

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

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

With no annotations, the description carries the full behavioral burden, yet it says nothing about data freshness, whether records are live or cached, rate limits, required entitlements, or failure behavior when a county lacks a 311 feed. It does disclose the substantive behavior (data aggregation plus deduction calculation plus document generation), which is worth some credit, but the operational profile is silent.

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 front-loaded sentence with the action and the outcome stated up front; the statutory citations are dense but they carry real meaning for an agent deciding relevance. No filler or restatement of the name.

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

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

For a 6-parameter, no-output-schema tool with no annotations, the description covers what is computed and what artifact is produced (Exhibit B-1 as json or html via the schema) but omits jurisdiction coverage limits and the shape of returned deduction data. Adequate to decide relevance, thin for confident execution.

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

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

Schema description coverage is 100%, so the schema already documents parcel_id, address, jurisdiction, county, market_value, and the json/html format switch. The description adds only indirect signal — 'calculate statutory obsolescence deductions' hints that market_value feeds the math — without naming or clarifying any parameter.

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

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

States a specific verb plus resource ('Audit a parcel') and enumerates the exact data sources it consults (municipal code enforcement, 311 blight databases, unfit dwellings, demolition orders, exterior violations). It also names the concrete deliverable (Exhibit B-1 with statutory obsolescence deductions), distinguishing it from adjacent siblings like audit_municipal_permits or get_condition_evidence_catalog.

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 blight/code-enforcement focus implies when to reach for it, but there is no explicit when-to-use/when-not-to-use guidance and no mention of alternatives among the many audit_* siblings. An agent must infer selection from the legal citations alone.

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

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

No annotations are provided, so the description must carry the behavioral burden. It discloses the external SSURGO dependency and that the tool detects misclassifications and calculates overcharges, but it does not explicitly state read-only status, permission requirements, failure modes, or whether any records are modified.

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?

It is a single front-loaded sentence with no wasted clauses, and the core action is clear immediately. It is slightly dense due to the statutory citation and Exhibit G reference, but each clause contributes domain specificity.

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

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

There is no output schema and no annotations, so the description should explain what the audit returns, how Exhibit G output is produced, and key limitations or prerequisites. It identifies the domain purpose but leaves an agent without enough behavioral and output context to call it confidently beyond the parameter schema.

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

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

Schema description coverage is 100%, so all seven parameters are already documented in the schema. The description does not add format, constraints, or usage notes beyond naming the audited parcel, so the baseline of 3 is appropriate.

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

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

The description states a specific verb and resource: auditing a parcel against USDA NRCS SSURGO soil data for Greenbelt misclassification, soil capability classes, and statutory overcharges. This clearly differentiates it from tax-focused or topography-focused siblings such as audit_property_tax and audit_parcel_topography.

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 implies the use case: a parcel with possible Greenbelt agricultural productivity misclassification and present-use overcharge exposure. However, it does not explicitly say when to use this rather than siblings like check_eligibility, audit_property_tax, or audit_parcel_topography, nor does it state prerequisites such as Greenbelt enrollment.

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 bears the behavioral burden. It usefully discloses authoritative external data sources and the quantification logic, but it does not state whether the operation is read-only, what permissions or costs are involved, or what side effects, if any, occur.

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 with no filler and includes the key domain-specific details. It is dense but appropriately sized for a specialized audit tool, though it could be slightly easier to scan with a little structural separation.

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 complex audit purpose, rich input schema, and absence of both annotations and an output schema, the description covers what the tool analyzes but not what the returned audit contains. An agent can identify the tool, but the description leaves gaps around output shape and operational behavior.

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

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

Schema description coverage is 100%, so all eight parameters are already documented in the input schema. The description does not add parameter-specific semantics beyond indirectly referencing Exhibit T, making the baseline 3 appropriate.

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

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

The description uses a specific verb and resource ('Audit a parcel against ... topography') and names the exact impairments quantified: steep slope >25% grade and sinkhole land impairments. It also differentiates itself from sibling parcel audits by focusing on USGS 3DEP LiDAR and karst subsidence data rather than soil, flood, blight, or valuation checks.

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

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

The description provides a clear use context: producing Board-admissible adverse topography adjustments (Exhibit T). It does not explicitly state when not to use this tool or name alternative sibling audits, so it falls short of full when/when-not 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 provided, so the description carries the full behavioral burden. It says 'batch ingest' without stating whether ingested properties persist into a portfolio, whether the operation is read-only computation, what permissions or credits are required, or how malformed rows are handled — all material for a bulk write/analysis tool. It adds some value by bounding batch size and naming the computed metrics, but persistence and failure semantics are unaddressed.

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 dense sentence front-loaded with the verb and the batch-size constraint, followed by the output summary — no boilerplate or filler. The enumerated metric list is long but each item conveys a distinct return 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?

With no output schema, the description usefully enumerates what comes back (equity, overassessment delta, recovery estimate, ranked targets), and sync/async behavior is covered by the async_task schema entry. Remaining gaps are persistence of the ingested batch and error handling for invalid rows, which an agent needs before submitting 500 records.

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

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

Schema description coverage is 100%, so the baseline is 3; each parameter including async_task behavior and required CSV headers is already documented in the schema. The description adds only the framing that inputs arrive as CSV text or a JSON array and omits the third intake route (text_addresses) and the co-branding params (realtor_name, brokerage_name).

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

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

States a specific verb+resource ('Batch ingest and analyze 10–500 properties') plus the accepted input formats and the exact computed outputs (comparable sales equity, overassessment delta, annual tax recovery, ranked targets). This clearly separates it from single-parcel siblings like audit_property_tax and from selection tools like curate_portfolio_selection.

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?

Gives a concrete usage envelope: 10–500 properties, CSV text or JSON array, aimed at agents/brokers/landlords performing portfolio-scale screening. It never names an alternative or exclusion (e.g., when to prefer single-property audit tools or a staging tool), so the boundary against siblings is left to inference.

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

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

With no annotations, the description must carry the full behavioral burden. It does add real context: it discloses that it works only 'where the supported evidence model permits', that unsupported items are held rather than asserted, and that it does not certify outcomes. However, it never explicitly states read-only status (only implied by 'Inspect'), nor permissions, side effects, or result shape.

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 purpose is front-loaded in the first clause, which is good. But the four-sentence body is dense with unparseable terms such as 'yard-item' and 'source-conflict holds', and the caveats consume more space than the actionable description, reducing 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?

For a complex, five-parameter tool with no annotations and no output schema, the description must explain both behavior and result. It sketches the deliverable ('draft building-assessment-equity comparison', separated rate scenarios versus unavailable savings) and the limits, but leaves the actual return structure and what counts as a 'hold' unexplained.

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

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

Schema description coverage is 100%, so the schema already documents all five parameters, and baseline 3 applies. The description alludes to concepts tied to notice_appraised_value and actual_sqft (rate scenarios, unknown-year/rate holds) but does not map them to parameters or add format/semantic detail 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 opening clause 'Inspect retained county assessments' names a specific verb and resource, but the remainder ('draft building-assessment-equity comparison', 'conditional rate scenarios', 'unknown-year/rate holds') is domain jargon that does not clarify what the tool operationally returns. It never distinguishes itself from close siblings like lookup_property_tax, get_property_assessment, or audit_square_footage_correction, so an agent cannot confidently choose it on purpose alone.

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

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

There is no statement of when to use this tool versus the many sibling audit/lookup tools, and no prerequisites are given. The closing sentence lists what the tool does NOT do (certify market value, benefits, filing, payment readiness), which is a scope exclusion rather than positive usage guidance.

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

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

No annotations are provided, so the description carries the full burden. It does disclose the data sources compared and the classes of discrepancies produced, but says nothing about whether the operation is read-only, what permissions or jurisdiction coverage it requires, how large a result set it returns, or what happens when the optional roll fields are omitted.

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 dense sentence with the action and the comparison front-loaded, then the three finding types. Efficient, though the statutory citations and jargon (Exhibit N, nominal consideration) add bulk that only specialists will parse quickly.

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

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

With no output schema and no annotations, the description must convey what the tool yields, and it does so by naming the three audit findings it surfaces, plus the legal hook for the Exhibit N case. Gaps remain on return shape, volume, and permissions, but the core is covered for a 3-parameter read-style audit.

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

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

Schema description coverage is 100%, so the schema already explains parcel_id as subject parcel/ID-or-address and the two optional current roll fields. The description adds conceptual meaning by framing those roll values as the comparison baseline for drift detection, though it never names the parameters explicitly.

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?

Specific verb+resource: auditing recent deeds and real estate transfer tax filings against county tax rolls, with three named finding types (deed backlogs, mailing address drift, nominal consideration transfers). Scope is concrete enough to separate it from generic siblings like audit_property_tax, but no sibling is named or excluded explicitly.

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?

Usage context is implied by the described inputs and findings (use when verifying deed/transfer records against the roll), and the Exhibit N / T.C.A. citations hint at an appeal-evidence scenario. However, there is no explicit when-to-use, no prerequisites, and no routing against the many sibling audit_* tools an agent must choose between.

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

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

No annotations are provided, so the description carries the full disclosure burden. It indicates the tool produces a 'County Trustee demand voucher,' but does not state whether it files anything, what permissions are required, whether the operation is reversible, or what the response contains – significant gaps for a tool that formats and potentially submits a legal demand document.

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 dense sentence with the action, legal authority (T.C.A. § 67-5-509), and trigger front-loaded. It earns its space, though the legal citations and nested clauses make it slightly heavy for one sentence.

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 gives legal basis and the triggering condition, adequate to understand purpose. But for a 10-parameter, no-annotation, no-output-schema tool, it omits the side-effect profile, expected result shape, and eligibility-verdict behavior that an agent needs before invoking.

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 10 well-described parameters, so the schema already documents each field. The description adds no parameter-level meaning (e.g., how tax_years_pending interacts with va_effective_date), so the baseline 3 applies.

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

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

States specific verbs ('audit eligibility' and 'format County Trustee demand voucher') against a precise resource (retroactive property tax refunds) and names the triggering condition (retroactive VA effective date). Among the many veteran-related siblings, the retroactive-refund trigger makes it distinct without needing to name an alternative.

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

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

The phrase 'when a veteran receives a retroactive VA effective date' implies the usage context, so the trigger is inferable. However, there is no explicit when-to-use vs. when-not guidance and no routing to alternatives like verify_va_disability_exemption or audit_disabled_veteran_relief, which overlap in veteran relief space.

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 load: it does disclose that this is a mutation with real consequences (enforce, strip penalties, issue injunction), which is valuable. It says nothing about required documentation, authorization, whether enforcement is actual or simulated, or how the injunction is served, leaving significant gaps for a write 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?

A single dense sentence with zero filler, front-loading the statutory basis and the enforcement outcome. Every clause maps to a distinct capability of the tool.

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 an 11-parameter mutation tool with no annotations and no output schema, one sentence is thin: it omits what the audit returns, what enforcement artifacts are produced, and the relationship between the two required fields (servicemember_name, active_duty_start_date) and the computations. Adequate but with clear 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 description coverage is 100%, so the schema already documents all 11 parameters with examples (e.g. interest rate as 0.18, date formats). The description adds one piece of semantics the schema does not: the 6% statutory cap that contextualizes county_interest_rate_annual and the penalty stripping that relates to billed_accrued_interest_and_penalties.

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?

Names a specific verb pair (audit and enforce) and a precisely scoped resource: the SCRA 6% delinquent property tax interest cap, cited to statute. The added actions (strip penalties, issue stay of tax sale injunction) make it distinguishable from siblings like audit_property_tax or audit_combat_deployment_abatement.

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 statute and the 'delinquent property tax' framing imply when the tool applies, but there is no explicit routing guidance versus audit_property_tax, check_delinquent_taxes, or the other veteran-relief auditors. An agent must infer selection from the mention of servicemember status and a county interest rate.

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 carry the behavioral burden. It discloses that the tool audits eligibility, calculates projected 5-year savings, and references base-year locking under the statute, but it does not clarify whether the operation is read-only, what permissions are required, how ineligible cases are handled, or what assumptions drive the savings projection.

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 compact sentence that front-loads the primary actions and names the program and statute without wasted text. The statutory citation and base-year reference are dense but directly relevant to the tool's scope.

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

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

For a statutory eligibility-and-savings calculation with seven parameters, no output schema, and no annotations, the description is somewhat thin. It names the program and the five-year projection, but it does not explain the output structure, calculation assumptions, or eligibility decision details that 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 description coverage is 100%, so the schema already documents all seven parameters, including the $45,000 income ceiling. The description adds program context such as the five-year projection horizon and base-year lock, but it does not add parameter-specific meaning beyond the schema.

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

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

The description uses specific verbs, 'Audit eligibility' and 'calculate projected 5-year savings,' for a clearly named program: the Tennessee Senior Property Tax Freeze. It also cites the governing statute, which distinguishes it from sibling relief tools such as disabled homeowner, disabled veteran, and surviving spouse programs.

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 intended use is implied by the program name and the eligibility-audit framing, but the description does not explicitly state when to use this tool versus siblings like check_eligibility or audit_property_tax. It also does not spell out prerequisites such as age thresholds or the income ceiling, though the income ceiling appears in the schema.

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

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

No annotations are provided, so the description carries the full disclosure burden. It says a petition is generated under a specific statute, but it does not say whether the petition is merely drafted or filed, what permissions or prerequisites are needed, what the response contains, or what side effects occur.

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 with the core action and legal context front-loaded, followed by clarifying examples. There is no redundant or filler text.

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

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

This is a complex legal-petition generation tool with seven parameters, no output schema, and no annotations. The description explains the purpose but leaves important runtime context unstated, especially what the tool returns and whether it performs any filing or mutation.

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

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

Schema description coverage is 100%, so the parameter meanings are already well documented. The description's square-footage example loosely connects to county_card_sqft, actual_measured_sqft, and discrepancy_reason, but it does not add meaning beyond the schema.

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

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

The description states a specific action ('Audit and generate a Property Record Correction Petition') tied to a specific legal basis and a narrowly defined error type ('mass-appraisal square footage errors'). The examples of screened porches or unfinished areas counted as heated GLA make it clearly distinct from broader audit siblings such as audit_property_tax.

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 gives a clear use case: square footage errors where county card GLA overstates heated living area, with concrete examples. It does not name alternatives or exclusions, so it falls short of a 5 but provides enough context to select it.

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

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

No annotations are provided, so the description carries the full behavioral burden. It does not disclose what the 'audit' step validates, what the generated certificate contains or whether it is a filing-ready artifact, how a false is_unremarried is handled, whether cross-state TX/FL scenarios are supported, or whether the call is a pure read or has 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?

A single front-loaded sentence with no filler; the purpose and statutory basis arrive immediately. It is dense with legal citations but nothing is redundant.

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 10-parameter, 6-required legal-document generation tool with no annotations and no output schema, the description should explain what the certificate output looks like and what the audit checks. Those gaps, plus the missing differentiation from the surviving-spouse sibling, leave an agent under-informed before invocation.

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

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

Schema description coverage is 100%, so every one of the 10 parameters is already documented in the schema, which sets the baseline at 3. The description adds only the general notion of carrying a certified amount from a prior parcel to a new one, without adding format, units, or constraint detail 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?

States a concrete verb pair (audit and generate) plus a specific artifact (Certificate of Surviving Spouse Homestead Exemption Portability & Transfer) with statutory grounding in Tex. Tax Code § 11.131(d) and Fla. Stat. § 196.081(3). It is clear what the tool does, but it never distinguishes itself from the close sibling audit_surviving_spouse_vet_relief, which an agent could easily confuse it with.

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

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

There is no explicit when-to-use or when-not-to-use guidance, no prerequisite framing, and no mention of alternatives such as audit_surviving_spouse_vet_relief, check_eligibility, or check_veteran_relief. The only usage signal is implicit in the phrase 'to carry over certified tax exemption to a new primary residence'.

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

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

No annotations are provided, so the description carries the full burden. It does disclose one real behavioral trait beyond the schema: the tool produces a Form F-16 application document, not just a boolean eligibility verdict. However, it says nothing about what happens when the spouse fails eligibility, whether the generated form is persisted or returned, or what permissions/documents are required.

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 dense sentence that front-loads the two actions and then narrows to the eligible population and the governing statute. No filler and no restatement of the tool name.

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

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

With 8 parameters, no annotations, and no output schema, the description should say more about the return value (eligibility result plus a generated form artifact) and failure paths. The statutory scope is well covered, but the artifact-generation behavior an agent needs in order to consume the result is left unspecified.

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

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

Schema description coverage is 100%, so all 8 parameters are already documented in the schema and the baseline is 3. The description adds context for the statutory conditions behind is_unremarried and is_primary_residence (100% P&T / KIA, § 67-5-704(b)), but contributes no format or dependency detail for parcel_id or market_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?

States a specific compound verb (audit eligibility + generate Form F-16 application), the precise resource (property tax relief under T.C.A. § 67-5-704(b)), and the exact beneficiary class (unremarried surviving spouses of 100% P&T veterans or KIA service members). That beneficiary scope is enough to distinguish it from sibling relief tools like audit_disabled_veteran_relief and audit_surviving_spouse_portability without opening any schema.

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

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

The qualifying conditions (unremarried spouse, 100% P&T or KIA, statutory citation) imply when the tool applies, but there is no explicit when-to-use/when-not statement and no naming of alternatives among the many adjacent veteran and spouse relief tools. An agent must infer the routing from the beneficiary description alone.

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

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

No annotations are provided, so the description carries the full disclosure burden. It notes the $0.00 pro-bono nature of the exemption check, which is useful context, but says nothing about whether the document is stored, whether this is a read-only analysis, what happens on unreadable OCR input, or what the response contains.

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

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

Two sentences with the action and the domain of documents front-loaded; the second sentence carries the eligibility scope. The phrase 'using TypeSafe System One (Jev)' and the '$0.00 pro-bono statutory' framing are slightly promotional but still informative.

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

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

With no output schema and no annotations, the description should say what the audit returns (classification verdict, extracted ratings, eligibility determination). For an extract-and-classify tool with 2 inputs, the absence of any return-value or side-effect description leaves a real gap.

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

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

Schema description coverage is 100% for both parameters, so the baseline is 3. The description adds document-type context that clarifies what raw_ocr_text should contain (VA benefit summary, DD-214, rating code sheet), but it adds no format or length guidance 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 names specific verbs (audit, classify, extract) and concrete resources (VA award letters, DD-214s, rating code sheets), plus the backing system (TypeSafe System One / Jev). It does not differentiate itself from near-neighbors like parse_va_benefit_letter or verify_va_disability_exemption, so an agent must infer the boundary from the phrase 'audit ... with Jev'.

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?

Usage is only implied through the document types and the P&T/TDIU/DIC exemption purpose. There is no explicit statement of when to pick this over verify_va_disability_exemption or parse_va_benefit_letter, and no prerequisites or when-not conditions.

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

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

No annotations are provided, so the description carries the full burden. It does disclose a consequential behavior — that it drafts a statutory lender demand letter, not just computes a number — and cites § 3729(c), which is real added context. However it never says whether the letter is returned, saved, or sent, nor whether ineligibility is reported, so material behavioral gaps remain.

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 with no filler, front-loaded on the audit verb and the refund subject. It is dense enough that the second half (statute citation plus eligibility condition) requires a careful read, which keeps it from a 5.

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

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

Eight parameters with seven required is a substantial schema, and with no output schema and no annotations the description should say what comes back (an eligibility determination? a letter body?). The statutory citation lets an agent route correctly, but the output and the eligibility test itself are unspecified.

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

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

Schema description coverage is 100%, so all eight parameters are already documented, making the baseline 3. The description hints at the semantics that matter most — the interaction between rating_effective_date and closing_date that establishes retroactivity — but leaves the agent to infer that relationship rather than stating 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?

States two specific verbs (audit eligibility, draft demand letter) against a specific resource (VA Home Loan Funding Fee refund), with a named legal basis. It is clearly separable from siblings like verify_va_disability_exemption or audit_va_award_document_with_jev, though it never explicitly names a sibling to route against.

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

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

The phrase 'for veterans awarded retroactive service-connected disability ratings' implies the qualifying scenario, which is useful context. But there is no explicit when-not guidance, no alternatives named, and no statement of what to do if eligibility fails.

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

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

No annotations are provided, so the description carries the full burden. It says 'audit and format' but never says what the audit does when eligibility facts fail (the two boolean parameters), whether it produces a fillable document, a warning list, or a refusal, or whether anything is written/recorded. For a tool that generates a sworn legal affidavit, the behavioral profile is materially under-disclosed.

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 dense sentence with the purpose and legal basis front-loaded and no filler. It is jargon-heavy (statute citations, 'continued beneficial homestead occupancy'), but every clause earns its place given the domain.

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 nine parameters, no output schema, and no annotations, the description should say what the call returns and what happens on ineligible inputs. Neither is covered, so an agent cannot predict the result shape or failure behavior for a document-generation 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 all nine fields are already documented with types and meanings. The description adds no further semantics beyond naming the general domain, which meets the baseline for fully-covered schemas but nothing more.

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

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

States a specific verb ('audit and format') and a specific deliverable ('Sworn Affidavit of Continued Beneficial Homestead Occupancy') with the legal effect being pursued. It does not distinguish itself from close siblings such as audit_disabled_veteran_relief, audit_surviving_spouse_vet_relief, or audit_veteran_shield, so an agent cannot route between them on description alone.

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 trigger situation is implied clearly ('after deeding residence to a revocable living trust'), which is genuinely useful context. But there is no explicit when-not guidance, no statement of prerequisites (e.g., must the disability rating be verified first via verify_va_disability_exemption?), and no named alternative for non-trust cases.

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

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

No annotations are provided, so the description carries the full burden, and it does not disclose whether this tool is read-only or produces/records an exclusion filing, what permissions or documentation are required, whether results are persisted, or what happens on ineligible cases. The only behavioral signal is the word 'Audit', which implies analysis, but 'format' implies a possible write — the ambiguity is unresolved.

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?

It is a single front-loaded sentence with no filler, which is good, but it is heavily compressed statutory jargon packed into one clause, making the actual action harder to parse than necessary. No structural headings or sentence breaks for a tool with 9 parameters.

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 9-parameter, no-annotation, no-output-schema tool, the description omits what the tool returns (an eligibility determination? a formatted exclusion document? a tax savings figure?), how the statutory tests are applied, and what happens with the optional inputs. The legal citation alone does not give an agent enough to call this confidently.

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 every parameter (parcel_id, has_sah_or_sha_grant, va_disability_percentage, accessibility_improvements_cost, county_tax_rate, etc.) is already documented. The description adds only the statutory framework that gives those inputs meaning; it does not explain defaults, units, or how optional parameters change the computation. Baseline 3 applies.

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

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

The description names a specific resource (SAH / ADA accessibility assessment exclusion) and the two governing statutes (38 U.S.C. § 2101, T.C.A. § 67-5-601), plus the intended effect (excise mobility improvements from residential assessment). That is enough to distinguish it from neighbors like audit_disabled_veteran_relief or verify_va_disability_exemption. The compound verb 'Audit eligibility and format' is ambiguous, however — it is unclear whether 'format' means producing a filing document or normalizing data.

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

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

There is no explicit statement of when to choose this tool versus the many sibling relief/eligibility audits (audit_disabled_homeowner_relief, audit_disabled_veteran_relief, audit_combat_deployment_abatement, verify_va_disability_exemption). Usage is only inferable from the statutory citations and the phrase 'excise medically necessary mobility improvements' — no prerequisites, exclusions, or alternative routing 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?

Annotations already cover readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description still adds real behavior: unprovided facts remain unknown rather than being inferred or looked up, and the call triggers no provider request, document generation or filing. The one thing left unsaid is what a returned 'gap' record actually contains.

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?

Roughly fifty words, front-loaded with the action and immediately followed by the scope limits; every sentence carries a distinct constraint. It is lean for a 17-parameter tool, which is a virtue, though the final clause reads as a terse list.

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 all-optional parameters and no output schema, the description correctly sets expectations that unknowns stay unknown and that results are gaps not determinations. However, with no output schema it never characterizes the shape or contents of the returned gap review, leaving the agent to guess what a successful response looks like.

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 every field—including deprecated aliases and the ownership_relationship enum—is documented in the schema itself. The description only groups the inputs into applicant/property/residence/review-year/VA categories, which is mild reinforcement rather than new semantics, so the baseline 3 applies.

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

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

The verb+resource are specific: it reviews the completeness of supplied applicant, property, residence, review-year and VA answers, and explicitly states the output is a requirements-gap review rather than an eligibility determination. It does not name which veteran-related sibling (check_veteran_relief, verify_va_disability_exemption, audit_surviving_spouse_vet_relief) it replaces in which situation, so an agent must still infer the boundary from the negative framing.

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?

'Free screening; no provider request, document generation or filing' implies the pre-flight/pre-eligibility context, and 'not eligibility, savings, verified identity or filing authority' implies those jobs belong to other tools. But no sibling is named and no explicit when-to-use/when-not rule is given, so routing still depends on inference.

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

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

No annotations exist, so the description carries the full burden. It does disclose the substance of what is examined and surfaced — active trustee liens, accrued penalty/interest, multi-year exposure, Chancery Court foreclosure tax-sale risk — which gives useful behavioral context. It says nothing about data sources, freshness, failure modes, or that the operation 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?

A single front-loaded sentence with no filler; every clause names a distinct audited facet. It is dense and jurisdiction-flavored ('Chancery Court') but nothing is redundant.

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

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

With no annotations and no output schema, the description reasonably enumerates the kinds of findings returned, which partially compensates. But it leaves unresolved how the two optional parameters combine and unlike a tool with an output schema, return structure must be inferred.

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 both parameters carry examples, so the schema already documents the inputs. The description adds nothing about parameter behavior — notably it does not say whether parcel_id or property_address is preferred, or whether either alone is sufficient given that zero parameters are required.

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

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

States a specific verb ('Audit') and a specific resource (delinquent property tax liens, penalty/interest, multi-year exposure, foreclosure sale risk). An agent knows exactly what domain outcome this tool produces, though it never names or distinguishes itself from close siblings like audit_property_tax or lookup_property_tax.

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

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

There is no when-to-use, when-not-to-use, or alternative-tool guidance at all. With roughly 80 siblings including audit_property_tax, lookup_property_tax, and check_portfolio_address_status, the absence of routing guidance is a real gap; the enumerated risk facets only loosely imply the use case.

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 the full burden; it does disclose the geographic scope of the check and the two possible outcomes (inside launch area vs. waitlist-eligible), which is real behavioral context. However, it says nothing about the response shape, error behavior for malformed or out-of-state addresses, or whether the call has side effects (e.g., actually adding someone to a waitlist).

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 front-loaded sentence with the decision criterion and the geography stated immediately. No filler or repetition.

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

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

With no annotations and no output schema, the description should say what a result contains and whether the call is read-only or has side effects. It covers the input question well but leaves the return value and resolution status of out-of-area addresses unexplained, which is exactly what a caller of an eligibility gate needs.

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 single parameter carries its own format examples, so the description adds no parameter-level detail. Baseline 3 applies when the schema does all the work.

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

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

States a specific verb ('Check') and resource ('street address') with the precise decision being made: in-area vs. waitlist-eligible, naming the geography (Hamilton County, TN / Chattanooga). It does not explicitly contrast with the closely related siblings join_waitlist or suggest_addresses, so it falls short of full sibling differentiation.

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

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

Usage is only implied by the phrase 'eligible to join the expansion waitlist,' which hints that join_waitlist is the follow-up action, but the description never says when to call this versus join_waitlist or suggest_addresses. An agent must infer the workflow ordering.

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, but it does add real value by disclosing the return vocabulary ('verified_on_roll', 'watching_roll', 'stalled_needs_followup'), which tells the agent this is a read-style reconciliation check. It says nothing about record freshness, permission requirements, or whether it mutates state, leaving gaps for an unannotated 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?

A single sentence that leads with the action and then the return contract, with zero 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?

For a one-parameter tool with no output schema, the description usefully compensates by enumerating the return statuses, so an agent knows what a call yields. The main shortfall is the absence of usage/routing context, which keeps it from a 5.

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

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

Schema coverage is 100% and the parameter already documents its origin (generate_address_change_packet), so the description adds no parameter meaning beyond the schema. Baseline 3 applies.

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

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

States a specific verb (reconcile) and two concrete resources (address change orders vs. official county roll records), and even names the exact status values returned. An agent can distinguish this from write-side siblings like generate_address_change_packet or quote_address_change without opening the schema.

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

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

The description gives no explicit when-to-use, when-not-to-use, or alternative-tool guidance. The only routing signal (order_id comes from generate_address_change_packet) lives in the schema, not the description, and no sibling like quote_address_change is mentioned as a contrast.

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

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

Annotations already declare the tool as read-only, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful scope behavior: there is no default applicant or jurisdiction, and the tool does not make eligibility decisions, provide tax estimates, verify providers, generate documents or file anything.

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

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

The description is compact and front-loads the tool's purpose before listing exclusions. The second and third sentences are dense but purposeful, and no sentence is merely redundant with the title or annotations.

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, full schema coverage and annotations, the description is complete enough for correct tool selection. It could say more about the expected return shape for the missing-information screening, but the lack of an output schema and the clear scope boundaries make this a minor gap rather than a blocking one.

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 of the 17 parameters is already documented in the input schema. The description summarizes the parameter categories but does not add syntax, formatting or conflict-resolution details beyond the schema, so the baseline of 3 is appropriate.

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

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

The description states a specific verb and resource: screening supplied applicant, property, residence, review-year and VA-related answers for missing information before a program requirements review. It explicitly rules out adjacent capabilities such as eligibility decisions, tax estimates, provider verification, document generation and filing, which distinguishes it from sibling audit, eligibility and document-generation tools.

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

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

The description gives clear timing guidance: use it before a program requirements review to screen for missing information. It also lists what the tool does not do, implicitly steering eligibility, estimate, verification and filing work elsewhere, but it does not explicitly name the alternative sibling tools to use instead.

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

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

Annotations already mark it as non-read-only, idempotent, non-destructive, and open-world. The description adds important context beyond annotations: it records a simulated submission only, never submits a real appeal or changes county records, and requires sandbox authentication plus a completed test checkout.

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 tightly packed sentences with the action, behavioral limits, and prerequisites front-loaded. There is no wasted repetition or boilerplate.

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?

Covers the critical behavioral constraints for a sandbox finalization tool, including authentication, test-payment state, and simulation-only side effects. Without an output schema, it could say more about the returned packet/receipt or how to source order_id, so a small completeness gap remains.

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 only parameter is order_id, and the schema provides no description at all (0% coverage). The description says it is for “your own sandbox order,” which gives minimal context, but it does not explain the expected identifier format or where to obtain the order_id, so it does not compensate for the schema 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?

States a specific verb and resource: verify a fresh Stripe TEST payment for a sandbox order and release its draft packet and receipt. It implies this is the finalization step relative to start_tax_sandbox and get_tax_sandbox_order, but it does not name or explicitly distinguish those siblings.

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

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

Gives clear preconditions: owner:sandbox sign-in and a completed test checkout, and limits use to fresh Stripe TEST payments for your own sandbox order. It does not explicitly route the agent to start_tax_sandbox or get_tax_sandbox_order when those are the correct 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 carries the full disclosure burden. It usefully states that counts, total market value, and estimated annual tax recovery recalculate in real-time, but says nothing about the mutation consequences of remove/toggle, whether curation is persisted or reversible, what "auto" or the opaque "TypeSafe System One (Jev)" actually does, or any auth/rate constraints — a significant gap for a state-changing 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?

Two dense sentences, front-loaded with the core action and followed by the recalculated outputs. Every clause maps to a capability or side effect. Minor cost: the inline jargon "TypeSafe System One (Jev)" adds a name the agent cannot act on.

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 7-parameter, state-mutating tool with no annotations and no output schema, the description covers the action surface and the derived recalculations reasonably. It does not explain the return payload, what happens to the staged list after remove/toggle, or how it composes with stage_portfolio_selection, leaving a real gap 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%, so the baseline is 3, but the description genuinely adds meaning beyond the enum labels: it maps 'add'/'remove' to domain intent (new parcels vs. sold or NNN properties), 'set_homestead' to Primary Residence/Homestead HQ, and 'auto' to natural-language execution. It still leaves staging_id, client_name, and reason semantics entirely to 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?

Specific verb+resource ("curate a staged portfolio selection") with an enumerated action set: add parcels, remove sold/NNN properties, toggle, set Primary Residence/Homestead HQ, and NL execution. An agent knows exactly what the tool does. However, it never distinguishes itself from the closely-named sibling stage_portfolio_selection, so an agent must infer that this operates on an already-staged set rather than creating one.

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?

Usage is implied by "from previous staging/curation turn" in the schema and by "staged portfolio selection in Chat / MCP," suggesting it is a follow-on to staging. But there is no explicit when-to-use statement, no exclusion of stage_portfolio_selection or check_portfolio_address_status, and no prerequisite that a staging_id must already exist.

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

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

Annotations already cover readOnly/idempotent/non-destructive, so the description adds the valuable part: that matches do NOT establish ownership authority, assessments, savings, or filing eligibility and require user confirmation. It also says it returns 'matching reasons and source evidence.' Strong semantic disclosure beyond the safety profile, though it could note result volume/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?

Three sentences: purpose, then return content, then a disclaimer — well front-loaded and each sentence contributes. No padding, though the disclaimer sentence is somewhat 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?

For a read-only 2-param tool with no output schema, the description covers input intent, what is returned (matching reasons, source evidence), and the critical interpretation caveat. It stops short of describing match criteria or result cardinality, but is largely complete for correct invocation and interpretation.

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 'property' parameter is well-described in the schema ('Exact county account, GPIN or street address'), so the description rightly doesn't repeat it. The 'county_fips' enum (51153) has no schema description, but the description's 'Prince William County' phrasing contextualizes it. With 50% 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?

States a specific verb and resource ('Find possible related Prince William County properties'), the method ('from the retained county owner index'), and the input ('using a specific subject property'). This clearly distinguishes it from the many audit_/lookup_/recheck_ siblings that operate on a single property's tax or eligibility data.

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

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

The phrase 'using a specific subject property' implies the input context, but there is no explicit when-to-use guidance or named alternative (e.g., vs recheck_property_opportunities or suggest_addresses). The agent must infer when discovery of related properties is the right call over nearby tools.

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

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

No annotations are supplied, so the description must disclose operational behavior; it explains the modeling context but not whether the tool is read-only, has side effects, requires permissions, or returns only estimates. The legal and timing context is useful but insufficient for full behavioral transparency without annotations.

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

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

It is a single front-loaded sentence with no filler. Each clause identifies the statute, modeling basis, forecast outcomes, and timing.

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 definition gives enough domain framing to understand the forecast, and all input parameters are documented in the schema. However, with no output schema it does not describe the return structure, and with no annotations it leaves operational assumptions and proposed-rate sourcing unclear.

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

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

Schema coverage is 100% with descriptions for all five parameters, so the schema already carries the parameter semantics. The description adds domain context but does not clarify how 'proposed county/city tax rates' are supplied when no such parameter exists, so it does not improve on the baseline.

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

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

Names a specific verb ('Model') and a specific domain object ('Truth-in-Taxation revenue-neutral certified tax rates') plus the predicted outcomes ('bill shock and appeal savings'). It is clearly distinct from the sibling audit and lookup tools through its T.C.A. § 67-5-1701 forecasting framing, though it does not explicitly name an alternative tool.

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

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

The phrase 'before tax bills are mailed' gives a clear timing cue for when this forecast is relevant. It does not state when not to use it, prerequisites, or which sibling tools handle adjacent analyses such as reappraisal surge or property tax audits.

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 behavioral burden. It usefully names the receiving agency (NPRC St. Louis) and the record type, but it does not state whether the tool merely produces a fillable PDF for the user to mail or actually files a request with NPRC, nor what the caller gets back or any auth requirements. That leaves a meaningful behavioral gap for a document-generation 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?

A single dense sentence that front-loads the form name and resource. It is efficient and readable, though it packs several clauses (form, record copy, agency, purpose) that could be trimmed slightly without loss.

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

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

For a 10-parameter generation tool with no output schema and no annotations, the description explains the input side well via schema, but omits what the tool produces and whether it submits externally. That is a notable gap for a document/generation tool with zero annotation coverage.

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

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

Schema description coverage is 100%, so the schema already documents all 10 parameters with examples. The description adds domain framing but no parameter-level semantics beyond what the schema provides, so the 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?

States a specific verb (Generate) plus the exact resource (official SF-180), and clarifies the form's target record (DD-214 Member-4) and downstream purpose (property tax relief). This clearly separates it from siblings like generate_veteran_packet and generate_vso_referral, which produce different artifacts.

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

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

The description gives strong context (property tax relief, NPRC retrieval) that implies when the tool applies, but it never explicitly says when NOT to use it or which sibling (e.g., generate_veteran_packet, generate_vso_referral, run_veteran_pilot_flow) is the alternative for related requests. The routing is left to inference from the domain 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?

Annotations already declare read-only/idempotent/non-destructive, but the description adds critical context beyond them: despite the name, no documents are created, no email is sent, nothing is filed, and no savings or qualification decision is returned. For a tool whose name implies document generation, this disclosure is exactly what an agent needs.

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?

Four tight sentences with the scope disclaimer front-loaded ahead of navigation advice. The language is slightly jargon-laden ('supplied-fact screening,' 'protected property-workspace handoff') but nothing is expendable.

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, and the description states what is and isn't returned (screening gaps, review handoff, no eligibility decision), which covers the main gap. With 18 well-documented parameters and read-only annotations, only the shape of the returned screening output remains unspecified.

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% across 18 parameters, including deprecated aliases and their conflict behavior, so the schema does the heavy lifting. The description adds no per-parameter guidance, so the baseline 3 applies.

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

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

The description names the two outputs (supplied-fact screening, protected property-workspace handoff) and explicitly disclaims the misleading legacy name by saying it creates no documents, sends no email, and files nothing. It is distinguishable from document-producing siblings such as generate_sf180_request, though the terms 'screening' and 'handoff' are somewhat abstract.

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 gives a light usage cue ('Select the saved property and review supporting evidence in the browser') but never states when to choose this over run_veteran_pilot_flow, check_veteran_relief, or audit_surviving_spouse_vet_relief. Usage is implied rather than explicitly routed.

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

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

No annotations are provided, so the description carries the full disclosure burden. It signals the output is a 'pre-formatted' email and identifies the recipient class, which is useful, but it never clarifies whether the tool only drafts or actually sends the email, whether it resolves real VSO contacts from state/county, or what permissions or side effects are involved.

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 well-formed sentence that front-loads the action and artifact, then qualifies eligibility. No filler, nothing redundant.

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 7-parameter generation tool with no output schema and no annotations, the description leaves real gaps: zero parameters are marked required, so an agent cannot tell whether veteran_name or state/county are mandatory to produce a usable referral, and the return format is undescribed. The core use case is covered, but the call-shaping details are not.

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 every parameter is already documented, which sets the baseline at 3. The description adds only the 'rated under 100%' context that implicitly ties to va_disability_percentage; it does not explain why state_code and county_name matter (VSO lookup) or what format they take.

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

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

States a specific verb ('Generate') and a specific artifact ('pre-formatted warm referral email to an Accredited VSO'), plus the eligible VSO organizations and the two benefit tracks (rating increase, TDIU). It is clear on its own, but it never distinguishes itself from nearby generation siblings such as generate_veteran_packet or generate_sf180_request, which an agent must choose between.

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?

Gives a concrete trigger condition: use it for rating increase or TDIU review 'when a veteran is rated under 100%.' That is genuine when-to-use guidance. It stops short of naming alternatives or stating when-not-to-use (e.g., for veterans already at 100% or for other claim types).

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

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

No annotations are provided, so the description carries the behavioral burden. 'Retrieve' strongly implies a read-only reference lookup, and the description lists what content is included (deadlines, guarantee, escrow guidance), but it does not explicitly state read-only/non-destructive behavior, permissions, rate limits, or return format.

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

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

The description is a single front-loaded sentence that opens with the verb and resource, then lists the substantive content areas. Every clause adds meaning, and there is no filler.

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

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

With zero parameters and no output schema, the description appropriately enumerates the kinds of content returned: appeal ladder levels, deadlines, the Walk-Away Zero Guarantee, and escrow-versus-direct taxpayer guidance. It is complete enough to call, though it does not describe the precise return format or whether the content is static or jurisdiction-specific.

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

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

The tool has zero input parameters, so there is no parameter surface to document. The baseline for a parameterless tool is 4, and the description does not misrepresent any parameter 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 uses a specific verb, 'Retrieve,' and names the exact resource, the statutory multi-level appeal ladder, while enumerating the levels and included content. It is clearly distinguishable from sibling audit/check/lookup tools that focus on parcel, tax, veteran, or campaign analysis.

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

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

Usage is only implied by the content: an agent can infer this is for appeal-process reference. There is no explicit statement of when to use this versus siblings, no exclusions, and no alternatives named.

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 behavioral burden. It does disclose an important trait: the categories are unscreened and no determinations are established, which prevents an agent from treating output as findings. It omits return shape, size, and whether any auth or entitlement applies.

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 what the tool returns, then the caveats. The second sentence is a dense four-item negation list but every item carries distinct meaning, so little is wasted.

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

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

For a zero-param read tool with no output schema and no annotations, the description covers purpose and caveats but says nothing about what a checklist entry actually contains or how the catalog feeds the downstream defect-suggestion tool. That relationship is the main missing piece.

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

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

The tool takes zero parameters, so the schema has nothing to explain and there is no semantic gap for the description to fill. Baseline 4 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?

Specific verb plus resource ('Retrieve generic property-condition evidence checklists'), and the word 'generic' plus 'Categories have not been screened for any property' implicitly separates it from the property-specific sibling suggest_property_condition_defects. It never names that sibling outright, so differentiation is inferential rather than 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 disclaimer list ('No repair-cost, legal entitlement, market-value adjustment or tax deduction is established') implies this is a preparatory catalog lookup rather than an analysis tool, but the description never states when to reach for it or what to do next. Usage has to be reconstructed from the negative framing.

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 carry the behavioral burden. 'Retrieve' implies a read operation, but the description does not disclose permissions, data freshness, pagination, output shape, or other operational traits needed to understand behavior beyond the returned content categories.

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 with no filler. It states the resource, location, and key data categories efficiently, making every phrase count.

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

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

For a low-complexity, one-optional-parameter tool with rich schema coverage, the description covers the main purpose and data categories. However, with no annotations and no output schema, it does not provide return-format or operational context that an agent might need to interpret results confidently.

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

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

Schema description coverage is 100%, so the single optional 'submarket' parameter is already documented in the schema. The description mentions 'submarket breakdowns' but does not add syntax or filtering details beyond what the schema provides, making the baseline of 3 appropriate.

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

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

The description states a specific verb ('Retrieve') and resource ('historical property assessment roll analytics') with location ('Hamilton County, TN') and named data categories. It distinguishes the tool by county and by data scope, but it does not explicitly contrast with sibling analytics tools such as get_roll_analytics or get_knox_roll_analytics.

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 says what the tool retrieves but gives no guidance on when to use it versus alternatives like get_roll_analytics or get_knox_roll_analytics. There are no exclusions, prerequisites, or contextual usage conditions beyond the county name.

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 behavioral burden. It usefully enumerates what the payload contains (rules, ceilings, caps, review dates), which goes beyond the schema, but it omits important behavior: both parameters are optional, so it never says what happens with no arguments, nor whether results are county-level defaults, cached, or authoritative.

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 front-loaded sentence with the verb first and the returned artifacts listed efficiently. 'Comprehensive' is the one piece of filler, but nothing else wastes space.

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 no annotations, so the description is the only source of behavioral detail. It covers return content reasonably well but leaves the zero-required-parameter case and data precedence (state vs county granularity) unspecified — a real gap for a lookup whose inputs are both optional.

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 both parameters carry examples, so the schema already does this work. 'For any county/state' only restates scope; it adds no guidance on whether county can be supplied without state or how state-only requests resolve.

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

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

States a specific verb (Retrieve) and a concrete resource: statutory exemption rules, Senior Freeze ceilings, Disabled Veteran caps, and review dates scoped to a county/state. An agent can tell this is a jurisdiction-level reference lookup rather than a parcel-level audit like audit_senior_tax_freeze, though the description never names that distinction explicitly.

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 statement of when to use this versus the many audit_* relief tools that overlap in subject matter (senior freeze, disabled veteran relief, surviving spouse). 'For any county/state' implies jurisdiction-level scope but no exclusion or prerequisite 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?

With no annotations, the description carries the full burden. 'Retrieve' signals a read-only operation and the content categories (roll analytics, multi-cycle growth rates, submarket breakdowns) hint at what comes back, but there is nothing on permissions, cost, result size, or response shape for what is billed as a 'comprehensive' dataset.

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 front-loaded sentence with the county and core data categories up front; the parenthetical lists of years and city names add geographic concreteness at modest cost, though the sentence is 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?

There is no output schema and only one optional parameter, so the description only needs to convey scope and data types, which it does by naming growth cycles and submarket breakdowns; the lack of any return-format hint is a minor gap given the tool's breadth.

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% for the single optional submarket parameter, with concrete ID and zip-code examples, so the schema does the heavy lifting. The description's phrase 'submarket breakdowns' only loosely signals the parameter's role and adds no syntax or default 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 uses a specific verb ('Retrieve') and a well-defined resource (Knox County historical assessment roll analytics, growth rates, submarket breakdowns). The county qualifier distinguishes it from the sibling get_hamilton_roll_analytics and the generic get_roll_analytics, though it never names those alternatives directly.

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?

Usage is only implied through the 'Knox County' scoping; an agent can infer to use this instead of get_hamilton_roll_analytics for Knox data, but the description never states when to prefer it, or when to use the generic get_roll_analytics instead.

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 does disclose the key negative boundary ('no eligibility, pricing, savings, automatic refund or filing readiness is established'), which usefully frames the tool as a research/discovery read. However it never states that the operation is read-only or side-effect free, nor how results are structured beyond the status vocabulary (held/unavailable/evidence_required/not_screened).

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 filler, with the scope statement front-loaded and the limitation clause immediately after. Density of domain jargon slightly hurts readability but nothing is wasted.

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

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

There is no output schema, so the description must describe returns; it names the per-route status categories, which helps, but does not say what a 'route' record contains or how the catalog is ordered/paginated. Combined with the unstated name-to-content relationship, an agent has meaningful 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies a full-inventory, unfiltered read rather than a targeted lookup.

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 verb 'inspect' and resource 'evidence-gated research inventory of property-tax review routes and actual session tool availability' are specific but jargon-laden, and the description never reconciles with the tool name (get_microtransactions_catalog). An agent can tell roughly what class of data it returns, but the phrasing 'session tool availability' is opaque and does not clearly separate it from sibling 'audit_microtransaction' or 'get_condition_evidence_catalog'.

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

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

There is no statement of when to call this versus alternatives, no prerequisites, and no mention of the closely named sibling audit_microtransaction. The agent must infer usage purely from the resource label.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description still earns credit for adding an authorization requirement (live owner:read grant), a provenance warning ("user reports remain separate from county facts") and a note that mutations happen elsewhere in the protected browser review. It does not describe what the returned payload contains.

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, front-loaded with the read action and immediately followed by prerequisites. Some internal jargon ("source-bound service") adds length without adding agent-actionable meaning, but there is no filler.

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

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

With only two parameters and no output schema, the definition covers prerequisites, authorization and data provenance well. However, with no output schema the description should at least indicate what a "review detail" contains versus county facts, which it does not.

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 two patterned identifiers (intake_…, property_…) are undocumented in structured fields. The description partly compensates by saying both identifiers come from get_owner_workspace and that the review is explicitly selected, but it never distinguishes review_id from saved_property_id or explains the format constraints.

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?

"Read one explicitly selected saved property review" gives a specific verb (read), resource (saved property review) and scope (exactly one, pre-selected). It also ties itself to get_owner_workspace as the identifier source, which helps separate it from the audit_* / analytics siblings, though it never names a true alternative for review retrieval.

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

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

It states concrete preconditions: both identifiers must come from get_owner_workspace and a live owner:read grant is needed. "Explicitly selected" implicitly excludes browse/search usage, but there is no explicit when-not clause or named alternative 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?

Beyond the annotations, the description discloses the required owner-scoped grant, states that identifiers are returned explicitly, and clarifies that no active property is assumed. It also warns that the tool does not establish ownership, benefit eligibility, savings, or filing authority, adding useful behavioral boundaries for an owner-facing read.

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

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

The description is compact and front-loads the core action and auth context. The trailing disclaimer is useful but slightly dense; overall it avoids repetition and unnecessary detail.

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

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

For a zero-parameter read tool with full annotation coverage and no output schema, the description supplies the key context: auth grant, absence of an active property assumption, and the identifiers it returns. It does not describe pagination or result shape, but that is a minor gap given the tool's simplicity.

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

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

The tool has zero parameters, so the baseline is 4. The description does not need to describe parameter meanings and appropriately focuses on scope and output identifiers instead.

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 gives a specific verb and resource: reading the signed-in owner's actual saved property reviews and returning explicit property and review identifiers. This is clear enough to distinguish it from generic property lookup tools, though it does not explicitly contrast it with the closely related sibling get_owner_review_details.

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

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

It specifies an auth context ('revocable owner:read grant') and a scoping condition ('no active property is assumed'), and it rules out ownership, eligibility, savings, and filing authority. However, it does not explicitly say when to use this tool instead of nearby alternatives such as get_owner_review_details.

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 present, the description carries the full burden and does disclose non-obvious result semantics: unavailable facts stay unavailable (no fabrication), commercial source area is not finished living area, and comparisons are drafts with evidence holds. It omits read-only/auth/rate-limit behavior and return shape, keeping it from 5.

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

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

Three dense sentences with the core purpose front-loaded and caveats following. No filler, though the legalistic phrasing ('evidence holds', 'filing readiness') is slightly heavy.

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 no annotations, so the description must explain returns; it conveys caveats about result reliability but not what fields or structure an agent receives. Adequate but incomplete for a lookup tool with a five-parameter schema.

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

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

Schema description coverage is 100%, so every parameter is already documented (address, county_key, actual_sqft, address_or_pidn, notice_appraised_value). The description adds no parameter-level meaning beyond the schema, making baseline 3 correct.

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

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

States a specific verb ('Get') and resource ('retained county assessment observations and source provenance') scoped to 'a supported address or parcel ID'. An agent knows what kind of data comes back. It stops short of differentiating from siblings like get_property_model_readiness or lookup_property_tax, so not a 5.

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

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

The 'for a supported address or parcel ID' phrasing implies the input precondition, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many sibling tools. Usage is inferable rather than stated.

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

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

With no annotations, the description carries the full burden, and it does disclose something useful: the output is diagnostic evidence-gap material (classification axes, missing evidence) rather than a savings or filing determination. It still says nothing about whether the lookup is read-only in practice, what happens when the address/PIDN is unknown or outside county_key, or any failure 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?

Two sentences with no padding, and the disclaimer is placed after the purpose. However, the first sentence is noun-stacked and information-poor for its length, so brevity does not translate into 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?

No annotations and no output schema means the description must describe what comes back, and it only gestures at it ('classification axes', 'missing evidence') without structure or format. Combined with an undocumented required parameter, an agent could call this but could not predict or interpret the result.

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 only 50%: county_key is well documented in the schema, but address_or_pidn has no schema description and the tool description never mentions either parameter. The dual address-or-PIDN format (and what a PIDN looks like) is left entirely unexplained, so the description fails to compensate for the coverage 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 verb is 'Inspect' but the resource is buried in jargon ('retained assessment/building observations, separate classification axes and method-specific missing evidence') that never resolves into a concrete, checkable operation. An agent cannot tell what this returns or how it differs from siblings like get_property_assessment or simulate_property_model, which sound like the same domain.

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 only usage framing is a restriction ('for local Development testing') plus an exclusion ('does not establish savings or filing readiness'). There is no positive guidance on when to call this versus the many audit_*/get_* assessment tools, and no prerequisites are stated.

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

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

No annotations are provided, so the description carries the full burden. It conveys that this is a static statutory reference lookup (implying a safe read), but says nothing about result breadth, whether all states are returned by default, or whether the statutory content is versioned/limited. Adequate but thin for a zero-annotation 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?

A single front-loaded sentence with no filler; the domain terms come first and the state examples come last as parenthetical illustration. Slightly list-dense but every clause identifies a distinct content category the tool returns.

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

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

For a one-optional-parameter reference tool this is close to sufficient, but with no output schema and no annotations the description should at least sketch what a result contains (per-state rule records, license requirement text, board names) so the agent knows what to expect. It enumerates topics but not the shape of the return.

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 state_code semantics (two-letter abbreviation, empty means all states) are already fully documented. The example states in the description reinforce but do not extend that. Baseline 3 applies.

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

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

Specific verb 'Look up' plus a precisely scoped resource: statutory property tax representation rules, licensing requirements, waiver statutes, and governing boards. This clearly separates it from lookup_property_tax (tax amounts) and the audit_* family. It falls short of 5 only because it does not name the closest sibling it contrasts with.

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?

Usage is implied by the reference-lookup framing, but there is no explicit when-to-use, when-not-to-use, or mention of any alternative tool. The agent must infer that this is for regulatory/representation questions rather than valuation or exemption questions.

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 the full disclosure burden, yet it says nothing about what 'analytics' actually contains (aggregates, time series, per-parcel roll history), what time span 'historical' covers, or response shape and size. 'Retrieve' implies a read, but that is inference rather than disclosure; permissions, rate limits, and failure modes for unsupported counties are unaddressed.

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 front-loaded sentence with the resource stated first and the county constraint trailing. Nothing is wasted, though its brevity is partly under-specification rather than disciplined economy.

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

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

With no output schema, no annotations, and vague 'analytics' terminology, the description leaves the agent unable to predict what the call returns or how to choose between this and the county-specific siblings. For a data-retrieval tool in a 50+ sibling namespace, it should do more.

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

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

Schema description coverage is 100% — both 'county' (with default 'hamilton') and the optional 'submarket' are documented in the schema, so the baseline is 3. The description reinforces the two supported county values but adds no meaning about what a submarket ID or zip code actually filters within roll analytics.

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

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

States a specific verb ('Retrieve') and resource ('historical property assessment roll analytics') with an explicit scope of Hamilton or Knox County, TN, so the agent knows exactly what data domain this covers. It does not, however, distinguish itself from the sibling tools get_hamilton_roll_analytics and get_knox_roll_analytics, which appear to cover the same ground per-county.

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

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

No when-to-use or when-not-to-use guidance is given, and the near-duplicate siblings get_hamilton_roll_analytics and get_knox_roll_analytics are never mentioned, leaving the agent to guess whether this unified tool supersedes them. There is also no guidance on when to supply a submarket versus omitting 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?

Annotations already declare readOnlyHint/idempotent/non-destructive, so the bar is lower, yet the description adds real context: the auth requirement and the warning that payment and draft delivery statuses do not imply production eligibility or county filing. That is a genuine interpretation caveat an agent would otherwise get wrong.

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

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

Three short sentences, zero filler, with the core action front-loaded before the auth requirement and the status caveat. Nothing could be cut without losing 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?

No output schema exists, so the description carries some burden for return semantics; it hints that statuses exist but never enumerates the fields returned. Combined with the undocumented order_id, an agent has the gist but not enough to call confidently.

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

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

The single parameter order_id has 0% schema description coverage, and the description never says what an order ID is, its format, or where to obtain one (e.g., from start_tax_sandbox). With low coverage the description must compensate, and it does not.

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

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

States a specific verb and resource ("Read your own isolated Untax test order") and adds the sandbox scoping that separates it from production lookups. It does not explicitly distinguish itself from the sibling start_tax_sandbox / complete_tax_sandbox_order pair, so it stops short of a 5.

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

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

"Requires owner:sandbox sign-in" gives a precondition for use, which implies who may call it. But there is no explicit guidance on when to read versus when to complete the order (complete_tax_sandbox_order) or start one, so alternatives are left to inference.

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

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

No annotations are provided, so the description carries the full burden. It adds genuine context by labeling the data 'real-time' and the samples 'anonymized', and it discloses the shape of the returned metrics; however it says nothing about permissions, scope of aggregation, rate limits, or whether the data is workspace-wide or global.

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 front-loaded sentence with the verb first and the metric list following; no filler or restated title. The enumeration is dense but every item names a distinct output dimension, so it earns its length.

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

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

With no output schema, the description correctly shouldered the job of describing return contents and does so by naming each metric. For a zero-required-parameter read tool this is nearly sufficient; only aggregation scope and data source are missing.

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

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

Schema coverage is 100% — the single parameter limit_recent is fully documented in the schema, including its default of 5. The description's phrase 'recent activity' loosely corresponds but adds no format or bounds information beyond the schema, so the baseline 3 applies.

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