Buildability™ — Property Zoning & Buildability™ Intelligence

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds valuable context beyond annotations: the ~20 second runtime, the breadth of sources (20+ government), and a summary of the returned report contents. This helps set accuracy expectations for the agent and user.

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 moderately long but well-structured with labeled sections (USE WHEN, RETURNS, time estimate). It front-loads the core purpose, and while the 'Replaces $3,500+ zoning consultant work' is promotional, it adds persuasive context without being overly verbose.

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

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

For a complex tool with no output schema, the description covers the essential context: what the report includes, what triggers its use, and the time delay. It is complete enough for an agent to invoke it correctly, though it does not detail score interpretation or potential error conditions.

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 for parameters is 100%, with the address and persona parameters already described in the input schema. The description does not add additional detail about parameter formats or persona effects beyond what the schema provides. Baseline of 3 is appropriate.

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

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

The description clearly states the tool's function: retrieving complete property intelligence for any U.S. address, listing the categories (zoning, buildability, flood risk, etc.) and data sources. It distinguishes itself from sibling tools by being the comprehensive report while siblings are focused 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 'USE WHEN' section explicitly lists trigger phrases and scenarios, giving clear context for when to deploy this tool. It stops short of naming specific alternative tools or explicit 'when not to use' conditions, though sibling names are available in 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 state readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds valuable context: it is a pure calculation tool, it does not query data, and it returns a specific set of outputs (max square feet, stories, envelope dimensions, coverage math). It does not discuss behavior with only the required lot_area supplied, but the annotation coverage lowers the burden.

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

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

The description uses clear labeled sections (USE WHEN / RETURNS) and front-loads the core purpose. It is somewhat longer than a minimal description, but every section earns its place by covering triggers, outputs, and scope. The final input-summary sentence is a useful recap rather than padding.

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

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

Given 7 parameters, no output schema, and strong annotations, the description does the essential work: it specifies return values, input categories, and confirms no data querying. It could add detail on how optional parameters interact (e.g., what happens if constraints are omitted or conflicting), but the overall context is sufficient 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?

The input schema has 100% description coverage for all 7 parameters, so baseline 3 is appropriate. The description only restates the input categories ('lot area, setbacks, FAR, height limit, and coverage') without adding new parameter-specific details, examples, or default behaviors.

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

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

The description opens with a specific verb and resource: 'Calculate the maximum buildable area (building envelope) for a lot given zoning constraints.' It clearly distinguishes from siblings by stating it is 'a pure calculation tool, does not query data,' setting it apart from lookup_zoning and analyze_property.

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 an explicit 'USE WHEN' section with concrete user phrases ('how much can I build', 'max square footage') and clarifies this is for modeling existing dimensions/zoning rules. It does not explicitly name alternative tools, but the 'does not query data' contrast gives agents a clear signal about 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 declare readOnlyHint, openWorldHint, and idempotentHint, covering the safety profile. The description adds that it synthesizes data from multiple federal sources and returns a combined risk score, but it doesn't disclose limitations or what the output means beyond the list. No contradiction.

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

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

The description is well-structured with a main action, USE WHEN, and RETURNS sections. It is front-loaded with the primary purpose, and every sentence adds value without redundancy or fluff.

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

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

For a tool with no output schema, the description lists return elements (wildfire hazard zone, seismic risk zone, EPA contamination site proximity, radon zone level, soil concerns, combined risk score) and data sources, which is comprehensive. Minor gaps: it doesn't explicitly state U.S.-only scope or how the combined risk score is calculated.

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 descriptions cover all three parameters (address, latitude, longitude) at 100%. The description only restates that an address OR coordinates are accepted, which adds no meaning beyond the schema's 'preferred' and 'use if no address' notes. Baseline 3 is appropriate.

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

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

The description clearly states it 'Run full environmental risk screening for a property using EPA, USGS, NOAA, and USDA data' and lists specific hazard categories (wildfire, seismic, contamination, radon, soil). This specific verb+resource+scope distinguishes it from siblings like check_flood_zone which are narrower.

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 'USE WHEN' section with explicit trigger phrases ('environmental hazards', 'wildfire risk', 'contamination', 'is this area safe'), giving clear context for when to invoke. However, it does not mention when not to use it or alternatives like check_flood_zone for flood-only queries, so it lacks exclusions.

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

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

The description discloses what the tool returns (zone code, insurance requirement, base flood elevation, annual probability) and notes it uses the official FEMA API. This adds behavioral context beyond the annotations (readOnly, idempotent), which already indicate a safe read operation. It doesn't cover edge cases or errors, but given the strong annotation coverage, this 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 well-structured and front-loaded with the core purpose, followed by concise 'USE WHEN' and 'RETURNS' sections. Every sentence conveys necessary information (purpose, usage triggers, output details, data source) without redundancy, making it highly efficient.

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

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

The tool is simple (one parameter, no output schema), and the description covers the essential aspects: what it does, when to use it, and what it returns. It does not describe error handling or invalid address behavior, but for a low-complexity lookup tool with strong annotations, this is sufficiently 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 input schema already provides 100% coverage for the single parameter 'address' with a clear description ('Full U.S. property address'). The tool description adds context about U.S.-only usage and the FEMA API but does not add further parameter-level details like format examples or constraints, so the value added is minimal beyond the schema.

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

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

The description clearly states the tool's function: 'Check FEMA National Flood Hazard Layer for any U.S. property.' It is specific about the verb (check), resource (FEMA NFHL), and scope (any U.S. property), and it distinguishes itself from siblings like check_environmental_risks by focusing exclusively on flood zone data.

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

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

The description provides explicit 'USE WHEN' triggers with example user queries ('is this in a flood zone', 'do I need flood insurance', 'FEMA flood map'), giving clear guidance on when to invoke this tool. However, it does not explicitly mention when not to use it or alternative tools, 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 already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds that it returns a score, letter grade, band, and top 3 factors, and that it is faster than a full analysis. This provides behavioral context beyond the structured 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 structured with clear USE WHEN and RETURNS sections, making it skimmable. It contains some redundancy with the word 'quick' appearing multiple times, but every sentence contributes useful information, so it remains efficient.

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

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

Given the tool's simplicity (one parameter, no output schema), the description covers the purpose, usage conditions, return payload, and performance tradeoff. It is self-contained and provides all necessary information for an agent to select and invoke the tool.

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

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

The schema already fully describes the single 'address' parameter with 100% coverage. The description does not add additional details about the parameter, so it relies on the schema, meeting 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?

The description specifies the tool retrieves a Buildability Score (0-100) for a property, using the verb 'Get' and clearly identifying the resource and numeric range. It distinguishes from siblings by emphasizing it's a quick pre-screening tool and explicitly mentions being faster than analyze_property.

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 lists 'USE WHEN' scenarios and provides triggers like 'is this worth analyzing' and 'quick check on this address'. It also names analyze_property as a slower alternative for full analysis, giving clear context for when to choose this tool, though it lacks explicit when-not 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 declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, covering the safety profile. The description adds the output fields (zone code, setbacks, etc.) and U.S. coverage, but does not disclose potential limitations such as missing data for certain addresses or behavior for ambiguous inputs. This is a reasonable addition beyond annotations but not rich enough for a higher score.

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 with clear 'USE WHEN' and 'RETURNS' markers. It packs purpose, usage triggers, and return list into a compact format with no fluff, ensuring 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?

For a one-parameter lookup tool with no output schema, the description adequately covers the purpose, when to use it, and the return values. It does not discuss error handling or data availability, but for a simple read-only lookup these are not critical. Solid coverage with minor 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 input schema has 100% coverage for the single parameter, with 'Full U.S. property address' already described. The description's mention of 'any U.S. property address' adds minimal semantic value beyond the schema. Baseline 3 is appropriate when the schema carries the full weight.

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

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

The description opens with a specific verb ('look up') and target resource ('zoning designation and development standards') for any U.S. property address. It also lists example user queries like 'what zone is this' and 'can I build a duplex here', which clearly distinguishes it from sibling tools such as check_flood_zone or get_buildability_score.

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 'USE WHEN' section explicitly enumerates user intents and even includes 'or any question about permitted uses', giving clear context for when to invoke the tool. However, it does not explicitly mention when not to use or name alternative tools, 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 already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description adds value by detailing the exact output structure (subject property AVM, sales list with price/sqft/distance/beds/baths, rental comps, market stats), which goes beyond the annotations. It does not address rate limits or auth needs, but that is acceptable given it is a read-only open-world query.

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

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

The description is well-structured with 'USE WHEN' and 'RETURNS' sections, making it scannable and front-loaded with the core purpose. Every sentence contributes useful information—no fluff or repetition. It is appropriately sized for the tool's complexity.

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

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

Given no output schema, the description compensates by detailing return values. It covers purpose, usage triggers, and output content well. However, it does not explicitly state that at least one location parameter (address or lat/long) is required for a meaningful search, which is a notable gap for a tool with zero required parameters in the schema.

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

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

Schema coverage is 100%—each parameter has a description (e.g., address 'Full U.S. property address (preferred — gives best results)'). The description does not add much beyond the schema; it reiterates 'near a property' but does not clarify input constraints or parameter interplay. Baseline 3 is appropriate since 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?

The description opens with a specific verb+resource+scope: 'Find recent comparable property sales and rental comps near a property.' It clearly distinguishes from sibling tools like lookup_zoning or check_flood_zone by focusing on comparable sales data. The explicit list of user queries ('what are comps in this area', 'recent sales near here') reinforces the tool's purpose.

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

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

The 'USE WHEN' section provides explicit trigger phrases and use cases ('investor deal evaluation, CMA, and market analysis'), giving clear context for when to invoke the tool. However, it does not mention any exclusions or alternative sibling tools, so it stops short of full when-not-to-use guidance.

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

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

Beyond annotations (readOnlyHint=false, openWorldHint=true), the description adds substantial behavioral context: applied corrections within 48 hours, the correction feeds the Staff Responsiveness dimension, and it returns a correction ID with status. This provides a clear picture of side effects and expectations.

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

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

The description is well-structured and front-loaded with the core purpose. The 'USE WHEN' and 'RETURNS' sections are efficient and every sentence adds value, including the motivational 'USE ACTIVELY' which reinforces the tool's importance.

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

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

For a tool with 5 parameters, 2 required, and no output schema, the description provides comprehensive context: usage triggers, examples, the 48-hour SLA, the feedback loop, and the return format. Nothing critical is missing for an agent to decide when and how to use it.

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

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

Schema coverage is 100%, so every parameter is already documented in the input schema. The description adds no parameter-specific information beyond what the schema provides, meeting the baseline for high coverage.

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

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

The description opens with a specific verb and resource: 'Report an error on a Buildability™ page so Buildability™ can verify and update.' This clearly distinguishes the tool from siblings like analyze_property or lookup_zoning, which are analytical or informational rather than corrective.

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' with concrete examples of user-reported issues, and even encourages 'USE ACTIVELY'. However, it does not mention when not to use it or explicitly name alternative tools, so it falls just short of the highest bar.

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