Stratalize Real Estate

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds context about the data source (CBRE/JLL quarterly surveys) and intended audience, but does not disclose other behavioral traits such as output format, data recency, or geographic limitations, which are not addressed elsewhere.

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

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

The description is two sentences. The first states the tool's purpose; the second provides source and intended users. No filler or redundant content, and it is front-loaded with the essential 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?

For a simple read-only benchmark with three enum parameters and no output schema, the description provides adequate context: what the tool measures, data source, and use cases. It does not explicitly state that 'geography' is limited to US regions or what the output looks like, but these are minor gaps given the schema and annotations.

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

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

Schema description coverage is 0%, so the description is the only source. It lists the dimensions (asset class, market tier, geography) which maps to the schema parameters, but it does not add significant meaning beyond the parameter names and enums. The enums are mostly self-explanatory, but the description does not clarify relationships or provide guidance on combining filters.

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

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

The description clearly states the tool provides 'commercial real estate cap rate benchmarks' by asset class, market tier, and geography, mapping directly to its three parameters. It distinguishes from sibling benchmark tools by focusing specifically on cap rates, unlike get_construction_cost_benchmark or get_cre_debt_benchmark.

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 identifies target users (CRE acquisition teams, asset managers, real estate CFOs) and use cases (property pricing, portfolio valuation), providing clear context for when to use this tool. It does not explicitly name alternatives or list exclusions, but the context is sufficient for a specialized benchmark lookup.

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 safe read-only behavior. The description adds context beyond that by detailing the six perils, giving a rich example with specific metrics, and citing data sources. It does not contradict annotations and provides behavioral transparency about the output's nature.

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

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

The description is front-loaded with the usage context and purpose, followed by a helpful example and sources. It is somewhat lengthy but every section serves a purpose, making it effective rather than wasteful.

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

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

Since there is no output schema, the description compensates with a detailed example of the return value (EXTREME overall, hurricane percentile, flood zone, heat days). It also explains the data sources. While it lacks a precise return structure, the example sufficiently conveys what the agent can expect.

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

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

The schema covers 100% of the parameter description, so the baseline is 3. The description adds little about the 'location' parameter beyond the example 'Miami-Dade FL', which is consistent with the schema's 'US city and state' format but not a substantive addition.

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

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

The description clearly states the tool's function: 'Returns a composite risk score across six perils' for physical climate risk. It lists specific use cases and distinguishes itself from siblings by emphasizing the composite score built on FEMA's National Risk Index, setting it apart from tools like get_storm_event_history.

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 opens with 'Use when pricing physical climate risk for a location' and lists concrete scenarios (real estate acquisition, underwriting, construction site selection). However, it does not explicitly mention alternatives or when not to use this tool, so it falls short of a 5.

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

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description adds the data sources and content types. However, it does not disclose additional behavioral traits such as update frequency, data interpretation nuances, or any operational caveats, leaving the description to carry only modest extra context beyond annotations.

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

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

The description is concise and front-loaded, with the primary function clearly stated first. The source list and target audience add value without redundancy, resulting in an efficient and well-structured message.

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 the burden of explaining the return value. It lists the types of benchmarks and sources, which gives a good overview, but lacks detail on how construction_class influences output and what the result structure looks like. With the readOnly annotation, this is fairly complete but not exhaustive.

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

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

With 0% schema description coverage, the description partially compensates by mentioning 'building type and region' for hard cost per SF, but does not explain the 'construction_class' parameter or its relationship to the output. The enums provide options, but their significance is not clarified, leaving a gap in parameter understanding.

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

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

The description clearly identifies the tool's purpose: providing construction cost benchmarks with specific components (hard cost per SF, soft cost ratios, contingency standards, and material cost escalation signals). It distinguishes itself from sibling benchmark tools by focusing on construction costs.

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

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

The description implies usage for construction cost estimation, naming target audiences (developers, lenders, project owners), but does not explicitly state when to use this over other benchmark tools or mention any exclusions/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?

Annotations already mark this as read-only and non-destructive, so the bar for additional disclosure is lower. The description adds value by naming data sources (MBA CREF databook, Trepp public data) and explicitly listing the benchmark metrics, without contradicting 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?

The description is three concise sentences, front-loaded with the core purpose, then data source, then audience. Every sentence earns its place with no repetition or 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 simple read-only benchmark tool with two self-explanatory enum parameters and no output schema, the description covers purpose, metrics, sources, and audience. It could mention the response format (e.g., whether values are medians or ranges), but the listed metrics already imply the output structure.

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

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

The schema has 0% coverage and no inline property descriptions, so the description must compensate. It does by naming both parameters ('by property type and lender type') and giving examples of lender types. The enum values are self-explanatory, though the description does not explain each one or note that property_type is 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?

The description clearly states the tool returns commercial real estate debt benchmarks (DSCR minimums, LTV maximums, spread ranges) segmented by property type and lender type. This specific verb+resource combination differentiates it from sibling tools like get_real_estate_debt_stress_benchmark or get_mortgage_market_benchmark.

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

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

The description specifies the target audience ('CRE CFOs and capital markets teams structuring financings'), which implies when to use the tool. It does not explicitly mention alternatives or when-not-to-use, but the context is clear enough for an agent to select it for financing structuring scenarios.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the description does not need to state safety. It adds context about data sources (NAHB, ULI, industry composite) and the specific metrics returned, which is useful behavioral transparency beyond annotations. However, it does not describe return format or any limitations.

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

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

The description is a single, focused sentence that front-loads the core purpose and then adds target users and sources. Every clause adds value without redundancy, making it appropriately concise and well-structured.

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

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

The tool is simple with only 2 parameters and no output schema, so the description provides sufficient context for most use cases: it lists the metrics, target audience, and sources. It does not discuss market_tier selection or output details, but for a benchmark lookup tool, the description is reasonably complete.

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

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

Schema description coverage is 0%, so the description must compensate for parameter meanings. It mentions 'by product type' but does not elaborate on allowed values, and it completely omits the market_tier parameter. The enum values in the schema are self-explanatory, but the description fails to clarify how to combine them or what each parameter represents in the context of development benchmarks.

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

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

The description clearly identifies the tool as providing development pro forma benchmarks including yield on cost, profit-on-cost, construction-to-perm spread, and return hurdles by product type. It specifies the resource (development benchmarks) and the verb (get) implicitly, and distinguishes from sibling tools by focusing on development-specific metrics.

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 intended users and scenarios: 'For developers underwriting new projects and lenders sizing construction loans.' This gives clear context on when to use the tool, though it does not explicitly mention when not to use it or name alternative tools. Still, the audience and purpose are well-defined.

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 and destructiveHint=false. The description adds that the data is 'live' and sourced from FRED/Census, but it does not disclose response structure, update frequency, or limitations. With the annotations covering the safety profile, this is adequate but not especially rich.

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

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

The description is three sentences and front-loads the core function, then adds application and audience. It is appropriately sized with no filler, though the final sentence about target audience is somewhat promotional.

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

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

For a simple read-only tool with two optional enum parameters and no output schema, the description gives high-level context (indicators, source, use case) but omits return format and parameter guidance. It is minimally complete but leaves the agent to infer output structure from the tool name and general knowledge.

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

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

Schema description coverage is 0%, and the description does not explain the 'region' or 'structure_type' parameters. It even mentions 'by market tier,' which does not directly correspond to the provided enums (geographic regions and structure types), creating potential confusion. The description fails to compensate for the schema's lack of parameter descriptions.

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

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

The description clearly identifies the tool's resource: 'Live housing supply indicators — starts, permits, completions, and absorption' and names data sources (FRED and Census), which distinguishes it from sibling benchmark tools. It lacks an explicit verb like 'retrieves,' but the 'get_' prefix and concrete indicator list make the purpose evident.

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 provides clear usage context by stating the tool is 'a leading indicator for housing prices 6-12 months ahead' and names target audiences (developers, lenders, investors, housing policy analysts). It does not explicitly mention when not to use it or compare it to alternatives like get_residential_market_benchmark, so a small gap remains.

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 and destructiveHint=false, covering safety. The description adds that data comes from 'HUD annual FMR dataset' and is 'Free', which gives some context about data frequency and cost. However, it does not mention return format or response behavior (e.g., whether it returns a single value or a list), so it does not go beyond a minimal addition.

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

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

The description is four short sentences, front-loading the core purpose and then providing context. The final 'Free.' is a minor fragment but not harmful. The structure is efficient and readable, though slightly longer than necessary.

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

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

Given the tool's low complexity (2 params, no output schema), the description covers the data source, use cases, and cost, which is quite complete. It does not explain the return value format, but for a simple FMR lookup this is tolerable. The annotations cover safety, so the absence of output schema is less critical.

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

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

With schema description coverage at 50%, the description does mention both parameters ('metro area and bedroom count'), partially compensating. It does not clarify that bedroom_count is optional (only metro_area is required in schema), nor does it add any syntax or format details beyond the schema's example. The description adds some meaning but not enough to fully bridge the gap.

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

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

The description clearly identifies the resource ('HUD Fair Market Rents') and its two scoping dimensions ('by metro area and bedroom count'), which is specific and distinguishes it from sibling tools like get_rental_market_benchmark. However, it lacks an explicit action verb (e.g., 'retrieves'), relying on the tool name for that, so it falls just 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?

The description provides concrete use cases ('affordable housing underwriting', 'Section 8 compliance', 'LIHTC calculations', 'housing authority budgeting'), which clearly indicate when to use this tool. It does not name alternatives or state exclusions, but the use cases alone make the intended context clear.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds that the data is 'live' and updates weekly, sourced from FRED, which is useful behavioral context beyond the annotations without contradicting them.

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

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

The description is a single, information-dense sentence that front-loads the core purpose ('Live mortgage rate benchmarks') and then lists specific metrics in a compact list. The second sentence clarifies audience and update cadence. Every phrase earns its place, with no redundant wording.

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 outlines the data content and audience but omits any mention of the optional state and loan_type parameters, leaving the agent uncertain about request customization. No output schema exists, and the description does not explain return format or pagination, though the listed content gives some intuition.

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

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

Schema description coverage is 0%, meaning the description provides no explanation of the 'state' or 'loan_type' parameters. The schema itself lists 'state' as a generic string and 'loan_type' as an enum, but the description does not indicate whether these are filters, how to format state values, or what impact they have on results. This is a significant gap.

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

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

The description clearly identifies the tool as providing 'Live mortgage rate benchmarks' and enumerates specific components (30Y/15Y fixed, ARM spreads, DTI standards, etc.), which distinguishes it from sibling benchmark tools for other asset classes. The verb 'get' frames it as a retrieval operation, and the focus on mortgage-specific data separates it from cap rates, debt, or rental benchmarks.

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 names the target audience ('homebuyers, lenders, real estate agents, housing analysts') and notes weekly updates, providing some context. However, it does not explicitly state when to use this tool versus alternatives like get_cre_debt_benchmark, nor does it offer exclusions or guidance for selecting between the many sibling benchmark 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds context about the data source (NCREIF quarterly public data) and the type of returns included. It does not describe the return format, pagination, or any rate limits, but with annotations covering the main safety aspects, the additional source context is adequate.

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

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

The description is concise, with three sentences each contributing value: what the benchmark is, its standard status, and the data source and target audience. It is front-loaded with the most important information and contains 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?

Given no output schema and moderate complexity, the description provides a good overview of the tool's purpose and contents but lacks specific details about the period parameter and the exact output structure. The inclusion of the source frequency (quarterly) adds context, but the missing explanation of time ranges and return metrics leaves gaps for effective use.

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

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

Schema description coverage is 0%, so the description must compensate. It mentions 'by property type and region', which maps to the property_type and region parameters, but it does not mention the period parameter or clarify the meaning of values like '1y' or '3y'. It also doesn't explain that 'national' is an option or how regions are defined. Partial compensation, with a clear gap on the period 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 clearly specifies that this tool provides NCREIF Property Index institutional return benchmarks, including total returns, income returns, and appreciation, disaggregated by property type and region. This distinguishes it from sibling benchmark tools like get_reit_benchmark or get_cap_rate_benchmark by naming a specific index and data dimensions.

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

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

The description provides clear context by stating it is 'the standard benchmark for institutional real estate portfolios' and identifies the intended audience ('pension funds, endowments, and institutional asset managers'). However, it does not explicitly mention when to avoid this tool or direct users to alternatives such as get_reit_benchmark.

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 and destructiveHint=false, so the safety profile is clear. The description adds what to expect: event count, total losses, deaths, and historical context with 10-year trend acceleration, plus a concrete example. This is useful behavioral detail beyond 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?

The description is well-organized and front-loaded with the key use cases, then the data returned, a concrete example, and authoritative citations. Every sentence adds value, with no redundancy or fluff, making it appropriately sized for a specialized financial 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 a simple tool with one optional parameter and no output schema, the description gives enough context to understand the tool's purpose, data content, and a realistic example. The only notable gap is explicit parameter semantics, but the overall picture is fairly 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?

The schema has one parameter 'year' with no description (0% schema coverage). The description does not explicitly explain the year parameter; it only shows an example using 2023, implicitly suggesting year is an input. It does not clarify allowed values, default behavior, or format, so the description fails to compensate for the absent schema documentation.

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 ('Returns') and resource ('NOAA's official annual billion-dollar disaster economics'), clearly stating the tool's output. It distinguishes from siblings by focusing on macroeconomic loss data (event count, total losses, deaths) rather than event-level or risk-score data, and the use cases reinforce its unique role.

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

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

The description explicitly states 'Use when establishing the macroeconomic cost of climate risk' and lists concrete scenarios (ESG reporting, reinsurance, SEC/TCFD disclosures). It provides strong contextual guidance but does not mention when not to use the tool or name alternatives, so it stops short of a 5.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds useful context about data sources and metric types, but does not disclose behavioral details like response format, pagination, or time-period filtering.

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

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

The description is two sentences, front-loaded with the core purpose, followed by sources and target audience. Every sentence contributes meaning with no redundancy.

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

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

For a simple read-only tool with two parameters and no output schema, the description provides sufficient context: purpose, metrics, sources, and audience. It lacks explicit guidance on the optional market_tier parameter, but overall it is adequate for a tool of this complexity.

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

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

Schema description coverage is 0%, so the description must compensate. It mentions 'by property type' but does not explain the meaning of the property_type enum values or the optional market_tier parameter. The description adds minimal semantic value beyond the schema's structure.

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

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

The description clearly identifies that the tool provides property operating benchmarks, specifying concrete metrics (OpEx per SF, NOI margins, occupancy rates) and the resource (by property type). This distinguishes it from sibling benchmark tools that focus on other metrics like cap rates, construction costs, or debt.

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 names the target audience (asset managers, property managers, acquisition underwriters), which implies when the tool is relevant. However, it does not explicitly contrast with alternative sibling tools or state when not to use it.

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

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

Annotations already indicate a safe read-only operation. The description adds context about the data source and the specific metrics returned. It doesn't mention response format or error handling, but given the read-only nature, this is acceptable.

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, no fluff. The first sentence is highly informative, the second gives source credibility, and the third provides practical context. Every sentence earns its place.

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

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

The description covers the core output metrics and data source. It doesn't specify that state is required and property_type is optional (schema handles that), nor does it describe response format. Given the simple two-parameter query and read-only annotation, this is nearly 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 covers 'state' with a description, but 'property_type' lacks one. The description links both parameters to the output ('by state and property type'), partially compensating. However, it doesn't clarify that property_type is optional, and the enum values are self-explanatory.

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

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

The description clearly identifies the tool as providing property tax benchmarks, listing specific metrics (effective tax rates, assessment ratios, appeal success rates) and the resource (Lincoln Institute data). This distinguishes it from sibling benchmark tools such as cap rate or construction cost.

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 names the intended audience (property owners, asset managers, acquisition teams) and gives context about property tax being the largest controllable operating expense. This provides clear usage context, though it does not explicitly mention alternatives or when not to use the 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds useful behavioral context: data sources (FRED, CMBS) and a quarterly update note. However, it doesn't disclose response behavior, rate limits, or how scenario choices affect output, which would be valuable beyond 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?

The description is three concise sentences: the first states the core offering, the second names the audience, the third gives a key update frequency. Every sentence earns its place with no redundancy or 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 2 optional parameters and no output schema, the description provides a reasonable high-level overview of the data included. However, it does not explain how parameters filter the output, what the return format might be, or the significance of terms like 'maturity wall exposure' and 'stressed cap rate scenarios', leaving some ambiguity for an agent deciding if this tool fits the need.

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

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

Schema coverage is 0%, so the description must compensate. It indirectly references the parameters with 'stressed cap rate scenarios' and 'by property type', but does not explain the enum values (base/stress/severe_stress) or what each property type includes. This leaves significant semantic gaps for an agent.

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

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

The description clearly identifies the tool as providing CRE debt stress benchmarks, listing specific components (delinquency rate from FRED, CMBS delinquency by property type, maturity wall exposure, stressed cap rate scenarios). This specific detail distinguishes it from siblings like get_cre_debt_benchmark and get_cap_rate_benchmark.

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 names target users (lenders, special servicers, distressed investors, regulators) but does not explicitly state when to use this tool versus alternatives or when not to use it. No exclusions or comparisons to sibling tools are provided, so guidance is implied rather than explicit.

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

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds context about the data source (NAREIT monthly data) and that it is free, which is useful. However, it does not disclose return format, historical depth, or potential limitations, so behavioral transparency is only moderately enhanced.

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

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

The description is three sentences with the purpose front-loaded. It efficiently covers the tool's function, data source, and intended users. The 'Free' is slightly extraneous but does not detract significantly, making it concise without being overly terse.

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 tool with one parameter and no output schema, the description covers core purpose, audience, and source. However, it omits details about what the response contains (e.g., a single value vs. a time series) and any data range restrictions, which leaves some ambiguity for an agent invoking the tool.

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

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

The description says 'by property sector' but does not list the allowed enum values, even though schema description coverage is 0%. Since there is only one parameter and it is self-explanatory from the name, the description adds minimal value beyond the schema. The agent would need to inspect the enum to know valid sectors.

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

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

The description clearly states the tool provides REIT valuation and performance benchmarks, listing specific metrics like FFO multiples, AFFO multiples, dividend yields, NAV premium/discount, and total returns by property sector. This distinguishes it from sibling benchmark tools, which focus on other real estate metrics.

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 identifies the target audience (REIT analysts, portfolio managers, IR teams) and implies the tool is for obtaining REIT-specific benchmark data. It does not explicitly name alternatives or when-not-to-use cases, but the context is clear enough for an agent to select this tool over sibling benchmarks.

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 and destructiveHint=false, so the safety profile is clear. The description adds useful context about data sources (HUD, FRED, ApartmentList) and the live vacancy rate, but does not disclose any additional behavioral traits such as rate limits or response structure.

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 concise sentences that front-load the main output types and then provide sources and target audience. No redundant wording.

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

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

Given the tool is a read-only benchmark lookup with optional parameters, the description adequately lists the output types and sources. It doesn't describe return format or pagination, but that's less critical given the simple parameter set and annotations.

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

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

The description mentions 'by unit type' and 'by market tier', which correspond to the two schema parameters. However, it doesn't explain the meaning of specific enum values or how parameters interact, and with 0% schema description coverage, more detail would be helpful.

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

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

The description clearly states the tool provides rental market benchmarks including asking rents, vacancy rates, rent growth, and rent-to-income ratios. It doesn't explicitly distinguish from sibling tools like get_residential_market_benchmark, so it lacks 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?

The target audience is specified (landlords, investors, property managers), but there is no explicit guidance on when to use this tool versus alternatives like get_hud_fair_market_rent or get_residential_market_benchmark. The usage context is implied rather than explicit.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it is a safe read operation. The description adds useful context about data sources (FHFA HPI, FRED, Census) and the nature of the data, but it does not disclose return format, pagination, or other behavioral traits. Credit is given for source transparency, but the bar is lower due to annotations.

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

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

The description is two sentences, front-loaded with the core purpose. It efficiently lists metrics, sources, and audience without redundant words. Every clause earns its place.

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

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

Given the tool's simplicity (two optional enum parameters, no output schema, read-only annotations), the description provides adequate context about what data is returned (metrics list) and where it comes from. It does not describe the return structure, but the absence of an output schema makes that less critical. It is complete enough for an agent to select and invoke the tool correctly.

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

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

Schema description coverage is 0%, so the description must compensate for the two enum parameters. It partially explains 'market tier' through the phrase 'by market tier,' but it provides no explanation for the 'property_type' parameter. This leaves one parameter completely undocumented, which is a significant gap for a low-coverage schema.

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

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

The description clearly identifies the tool's purpose: providing residential real estate market benchmarks with a specific list of metrics (home price indices, price-to-rent ratios, etc.). This distinguishes it from sibling tools like get_cap_rate_benchmark or get_rental_market_benchmark, which focus on different benchmarks.

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 names the target audience ('residential investors, agents, developers, and housing analysts') and implies usage through the metric list, but it does not explicitly contrast with sibling benchmark tools or state when not to use it. The context is clear but lacks direct alternative guidance.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context about the data source (NOAA NCEI) and authority, but does not disclose potential limitations or behavioral nuances beyond what annotations imply. The added value is moderate, not rich.

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

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

The description is front-loaded with usage and purpose, includes a useful example and source. The 'cited by' sentence adds credibility but is not strictly necessary for tool invocation, making it slightly less concise than ideal.

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

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

Given no output schema, the description sufficiently explains return contents (frequency, losses, deaths, trend direction) and provides an example. It covers usage, output, and source but lacks explicit parameter details and potential 'when-not-to-use' guidance, which would make it more complete.

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

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

Schema coverage is 50%; state is described but years_back is not. The example ('Texas 10-year history') indirectly implies how parameters map, but the description never explicitly explains years_back. It adds some meaning beyond the schema but does not fully compensate for the gap.

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

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

The description clearly states what the tool returns: 'NOAA's official tally of billion-dollar weather disasters' with specific outputs (frequency, losses, deaths, trend). However, it does not explicitly distinguish itself from sibling tools like get_noaa_disaster_economics, so it lacks explicit 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?

The opening sentence gives explicit use cases: 'insurance underwriting, real estate acquisition due diligence, ESG climate risk disclosures, or board-level climate briefings.' It provides clear context but does not mention when not to use it or name alternatives, so it misses the top score.

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 indicate readOnlyHint=true and destructiveHint=false, and the description reinforces the read-only nature ('Returns... catalog'). It adds valuable behavioral context beyond annotations, such as pricing tiers and OAuth requirements, which are not derivable from schema or annotations.

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

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

The description is concise and well-structured: it starts with a clear directive ('START HERE'), then states the primary purpose, followed by access/pricing details, and ends with an actionable instruction. Every sentence adds information without redundancy.

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

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

Despite having no output schema and no parameters, the description is highly complete for a catalog overview tool. It covers purpose, usage, access/auth nuances, and how to navigate the tool ecosystem. This is sufficient for an agent to select and invoke it correctly.

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

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

The tool has zero parameters, so the schema provides no parameter semantics. Per the rubric, the baseline is 4 for zero parameters, and the description appropriately does not discuss parameters, implying the tool requires no input.

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

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

The description clearly states the tool 'Returns the complete Stratalize tool catalog', using a specific verb and resource. It distinguishes itself from sibling tools (which are individual data benchmarks) by being the overview/catalog tool, and explicitly positions itself as 'START HERE'.

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

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

It provides explicit usage guidance: 'Call this first to discover tools by role or vertical.' It also clarifies when different access methods (public MCP vs x402 vs OAuth) apply, which helps the agent decide how to invoke and what to expect.

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 readOnlyHint and destructiveHint annotations, the description details the exact analysis logic: NOAA data, specific thresholds (25 mph wind, 32°F freeze, precipitation probability), and the output structure (risk tier + high-risk days). It also provides a concrete example output and cites the data source, giving the agent a rich understanding of what to expect.

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

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

The description is four sentences and front-loads the primary use case. It includes an illustrative example and source attribution, all of which add value. While slightly longer than strictly necessary, every sentence serves a purpose and the structure is logical: use case, logic, example, source.

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 covers the tool's purpose, data source, thresholds, output format, and a worked example. There is no output schema, but the description compensates by describing the return. A minor gap is that it does not clarify how to choose between location vs lat/lon, or what happens if none are provided, even though all schema parameters are 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?

The input schema already provides 100% coverage with clear descriptions for lat, lon, and location, including example formats. The description adds a usage example (Chicago IL) but does not introduce new parameter meaning or clarify the optionality constraints (e.g., whether at least one input is required). It reinforces existing schema info but does not go beyond it.

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

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

The description clearly states the tool's function: it analyzes NOAA 7-day forecasts against construction delay thresholds (precipitation, wind speed, freeze events) and returns a risk tier plus high-risk days. It uses specific verbs and resources, and the example with Chicago IL makes the purpose immediately concrete. It also differentiates from siblings by focusing on short-term weather delay risk for construction, not benchmarks.

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 opens with explicit use cases: scheduling outdoor work, equipment deployment, and weather risk assessment for US sites. It gives clear context for when to use the tool. However, it does not explicitly name alternatives or when-not-to-use cases, though the sibling list (e.g., get_climate_risk_score) implies a distinction between short-term weather risk and other analytics.

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