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

Describes return content (capabilities, LLM guidance) and the output_mode parameter. No annotations provided, but description fully discloses behavior as a read-only listing.

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?

Front-loaded with purpose, followed by details and usage tips. Somewhat verbose with docstring format but every sentence adds value.

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

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

Complete for a discovery tool: lists what it returns (sources, tools, queries, spatial references, LLM guidance) and provides usage advice. No output schema needed as return is well-described.

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 'output_mode' is explained as 'Response format — "json" (default) or "text"', adding meaning beyond the schema which only has a default. With 0% schema coverage, description compensates adequately but is minimal.

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

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

Clearly states it lists full server capabilities including sources, tools, and supported queries. Distinguishes from sibling tools like her_search_monuments or her_export_geojson by being a meta tool for discovery.

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

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

Explicitly advises 'Call this once at the start of a session' to understand available tools and how to use them effectively, providing clear when-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?

Discloses that the tool is fast, returns a count, and no geometry. Lacks details on error handling or authentication, but for a simple count tool, the transparency is good.

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?

Well-structured with clear sections (Args, Returns, Tips). Every sentence is informative and concise without redundancy.

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

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

Given 4 parameters, no output schema, and no annotations, the description thoroughly explains the tool's purpose, parameter details, and usage scenario. The inclusion of a usage tip enhances completeness.

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

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

With 0% schema description coverage, the description fully compensates by specifying format for bbox (BNG coordinates), example values for monument_type and period, and options for output_mode. This adds crucial meaning beyond the bare schema.

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

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

The description clearly states it counts aerial mapping features in an area, emphasizes speed and no geometry return, and distinguishes itself from her_search_aerial by specifying the result is a count.

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

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

Explicitly advises using this tool before her_search_aerial to gauge result size, providing clear when-to-use guidance. Also includes a tip for LLMs to call it before fetching full records.

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

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

With no annotations, the description carries the full burden. It discloses that the tool is 'fast, no geometry returned' and specifies output modes ('json' or 'text'). This is good but could further clarify if the count is an estimate or exact, and any error conditions. Still, it provides useful behavioral context.

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

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

The description is concise and well-structured with a title line, args section, returns, and tips. Every sentence adds value, and the important information is front-loaded. No redundancy.

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

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

Given the tool's simplicity and lack of output schema, the description covers the key aspects: purpose, parameters, return value, and usage tips. It could note whether the count is exact or an estimate, but 'quick count' implies possible approximation. Overall, it is nearly complete for an agent to use correctly.

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

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

Input schema has 0% description coverage, so the description must compensate. It does so thoroughly: explains bbox format as 'xmin,ymin,xmax,ymax' in BNG (EPSG:27700), defines query as a name filter, lpa as Local Planning Authority filter, and output_mode as response format. This adds essential 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 clearly states 'Count conservation areas in an area' with added qualifiers 'fast, no geometry returned', which distinguishes it from sibling tools like her_search_conservation_areas that return full records. The verb and resource are specific and unambiguous.

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?

Explicit guidance is provided: 'Use before her_search_conservation_areas to gauge result size' and 'Tips for LLMs: Call this before her_search_conservation_areas to check how many areas match before fetching full records.' This tells the agent when to use this tool and when to use an alternative.

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

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

No annotations provided, so description carries full burden. Discloses it is fast, returns counts by designation type, and explains parameters. However, it does not mention potential limits on area size or count, nor pagination behavior. Still, it provides sufficient behavioral context for typical use.

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?

Concise and well-structured: a title line, brief paragraph, then Args and Returns sections, plus tips. Every sentence adds value with no redundancy. Front-loaded with 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?

All 3 parameters are described, return value is explained (counts by designation type), and performance tip is given. No output schema, but description covers what is needed. Given simplicity, it is 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 0%, but description compensates by explaining each parameter: designation_type filter semantics, bbox format in BNG, output_mode options. Adds meaning beyond type definitions.

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

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

Clearly states the tool counts heritage features in an area and returns counts by designation type. Distinguishes from search tools by emphasizing it doesn't fetch full records. The verb 'count' and resource 'heritage features' are specific, and it differentiates from sibling her_search_designations.

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

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

Explicitly advises to use this before her_search_designations to estimate result sizes, providing clear when-to-use guidance. Also suggests using it to decide whether to narrow search area. Sibling tool is named, giving actionable 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?

Discloses that it returns a quick count with no geometry, implying a read-only, fast operation. No annotations provided, so description carries burden, but lacks details on limitations or edge cases. Still adequate for the tool's simplicity.

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?

Well-structured with a one-line summary, bullet points for args/returns, and a tips section. Front-loaded, no unnecessary content.

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?

Complete for a simple count tool: explains inputs, output, and provides usage context. No output schema needed as return type is clear.

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?

Adds significant meaning to all three parameters: bbox format and CRS specified, heritage_category example given, output_mode options listed. Compensates fully for 0% schema description 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?

Clearly states it counts heritage at risk entries in an area, emphasizing speed and no geometry. Distinguishes from siblings like count tools for other entities and search functions.

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

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

Explicitly advises calling this before her_search_heritage_at_risk to gauge result size, providing clear when-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?

Describes the classification logic and data sources (NHLE, AIM, Gateway) but does not disclose any side effects, authorization requirements, or error handling. With no annotations, the burden is on the description, and it partially meets it.

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

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

Well-structured with separate sections for description, Args, Returns, and Tips. However, it is somewhat verbose for a tool description; some tips could be integrated into parameter descriptions. Still front-loaded and clear.

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

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

Given the complexity (7 parameters, no output schema), the description covers the input parameters fully but the return value description is minimal ('Classification of each candidate as match, near, or novel'). A more detailed output format or example would improve completeness.

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

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

All 7 parameters are explained in the Args section with types, defaults, and semantics. Schema description coverage is 0%, so the description fully compensates, adding significant value 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?

Clearly states the tool cross-references candidate locations against heritage assets and classifies them as match, near, or novel. However, it does not explicitly differentiate from the sibling her_crossref_map, leaving some ambiguity.

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

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

Provides explicit tips for LLMs: use BNG coordinates, set include_aim for LiDAR, and use her_enrich_gateway first for Gateway records. This gives clear usage context, though lacks explicit when-not-to-use.

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 adds visualization specifics (color-coded map) beyond the readOnlyHint annotation. It does not contradict annotations and provides context on output format, though lacks details on side effects or auth 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?

The description is two sentences, front-loaded with the core purpose, and contains no extraneous information. Every sentence is relevant.

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 6 unannotated parameters and no output schema, the description is incomplete. It omits parameter definitions, expected output format, and usage examples, leaving the agent with insufficient guidance for effective 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?

Despite 6 parameters with 0% schema coverage, the description provides no explanation of what parameters like basemap, candidates, or radius values do. The description fails to add any meaning beyond the input schema.

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

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

The description clearly states it visualizes cross-reference results as a color-coded map with specific colors for match types. It also mentions it runs the same analysis as her_cross_reference, distinguishing it from sibling 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 implies usage for visual mapping of cross-reference results, contrasting with her_cross_reference which likely provides data. However, it does not explicitly state when not to use it or provide alternatives beyond the sibling mention.

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

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

Discloses slowness (1-2 minutes), result filtering (only records with valid coordinates), and default behaviors. Lacks explicit safety statement but overall reveals key behavioral traits beyond the schema.

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?

Well-structured with sections, but some redundancy in tips (e.g., 'use before cross-reference' repeated). Still efficient and front-loaded with 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?

Explains return value shape (records with BNG coordinates) and relationship to her_cross_reference. Lacks output schema but provides enough context for effective use. Could detail record format, but sufficient given 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?

The 'Args' section explains all six parameters, including defaults and purpose, fully compensating for the 0% schema description coverage. Tips add practical guidance for fetch_details and output_mode.

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 'Fetch Heritage Gateway records with resolved coordinates', specifying verb (Fetch) and resource (Heritage Gateway records). It distinguishes from sibling her_search_heritage_gateway by emphasizing coordinate resolution and cross-referencing use.

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

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

Explicitly advises to use before her_cross_reference and suggests running her_search_monuments and her_search_aerial in parallel for comprehensive coverage. Provides clear when-to-use and 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 provided, so description carries full burden. Discloses output structure (easting/northing, fields) and bbox requirement. No contradictions. Adequate transparency for a read-like export 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?

Well-structured with intro, Args, Returns, and Tips sections. Slightly verbose with tips but each sentence adds value. No fluff.

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

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

Given 5 params and no output schema, description covers purpose, parameters, output format, and a prerequisite workflow. Lacks error handling but sufficient for typical 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 coverage is 0%, but description fully explains all 5 parameters with formats, defaults, and usage context (e.g., bbox format, gateway_sites as output of her_enrich_gateway). Adds significant meaning beyond raw 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?

Description clearly states 'Export heritage assets for LiDAR cross-referencing' with specific resource and format (chuk-mcp-lidar). Distinguishes from siblings like her_export_geojson by focusing on LiDAR spatial matching format.

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

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

Provides tips for LLMs (bbox required, use her_enrich_gateway first) which imply a workflow, but no explicit when-to-use vs alternatives like her_export_geojson or her_cross_reference.

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

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

Discloses output format (GeoJSON FeatureCollection), coordinate system (WGS84), default and maximum values for max_results, and output_mode options. However, with no annotations, the description does not indicate whether the tool is read-only or destructive, nor does it mention potential errors or rate 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?

Well-structured with a clear one-line purpose, followed by a short explanation, then a bulleted Arg list, Returns, and Tips. Every sentence adds value without redundancy.

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

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

Covers all parameters, output format, and practical tips. Given the lack of output schema and the tool's moderate complexity, the description is nearly complete. It misses error handling or permission context, but overall provides sufficient information 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?

Input schema has 0% description coverage, but the description's Args section fully compensates by explaining each parameter's purpose, format (e.g., bbox in BNG), default values, and options (e.g., output_mode). This provides complete semantic 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?

Clearly states the verb (export), resource (heritage assets), and output format (GeoJSON FeatureCollection). The description distinguishes this tool from the sibling her_export_for_lidar by specifying suitability for GIS tools like QGIS and Leaflet.

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?

Implies usage for exporting query results as GeoJSON, but does not explicitly state when to use this tool versus alternatives like her_export_for_lidar. The tips section provides some usage guidance (e.g., using bbox) but lacks exclusions or 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?

Despite no annotations, the description discloses behavioral traits such as input formats (accepting 'aim:HE_UID' or just HE_UID), output modes ('json' or 'text'), and return contents (monument type, period, etc.). It could be more explicit about idempotency or side effects, but the 'get' nature is implied.

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: clear purpose, args, returns, and tips. Every sentence adds value without redundancy.

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

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

For a simple retrieval tool with two parameters and no output schema, the description covers input formats, output modes, and return fields adequately. It could mention error handling for invalid IDs, but this is not essential for basic usage.

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 fully compensates by explaining record_id format with examples and output_mode options. This adds significant meaning beyond the bare 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 retrieves full details of a specific aerial mapping feature by its HE_UID. It explicitly distinguishes from sibling tools like her_search_aerial by focusing on a single record retrieval rather than search.

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 'Tips for LLMs' section explicitly directs agents to use record_id from her_search_aerial results, providing clear usage context. However, it does not mention when not to use the tool or alternative tools for similar purposes.

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

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

No annotations provided. Description covers input formats, output modes, and return content (name, LPA, location) but omits details like read-only nature, error handling, or rate 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?

Well-structured with sections, but could be slightly tighter. Every sentence adds value, including the LLM tips. Appropriate length for the tool's simplicity.

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?

Adequately describes return values ('Full details including name, LPA, location') despite no output schema. Context from siblings confirms it's a specific getter. Small gaps in behavior details.

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?

Adds significant value beyond schema (0% coverage). Explains record_id accepts 'ca:UID' or plain UID, and output_mode defaults, with examples.

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

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

Clearly states 'Get full details of a specific conservation area' using a specific verb and resource. Distinguishes itself from sibling search tools by focusing on retrieval by UID.

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

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

Provides clear context on when to use (retrieve by UID) and includes LLM tip to use record_id from search results. Does not explicitly state when not to use or compare to other get 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 provided, but the description discloses the return fields (category, risk methodology) and the nature of the operation (retrieval). It is transparent about inputs and outputs, though it doesn't mention error handling or 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 well-organized: a clear purpose, followed by a brief explanation, parameter list, return statement, and a targeted tip. Each sentence adds value without redundancy.

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

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

For a simple retrieve tool with 2 parameters and no output schema, the description covers the necessary details. It lists example inputs and mentions return fields, which is adequate for an agent to understand the tool's 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?

With 0% schema description coverage, the description fully compensates by explaining record_id as 'Heritage at Risk ID (e.g. har:1021506 or 1021506)' and output_mode as 'Response format — json (default) or text'. This adds essential meaning beyond the bare 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 'Get full details of a specific heritage at risk entry' and specifies retrieval by List Entry number. It distinguishes from sibling tools like her_search_heritage_at_risk by focusing on a single entry 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?

Explicitly tells LLMs to use record_id from her_search_heritage_at_risk results, and provides two acceptable formats for the ID. This gives direct guidance on when and how 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?

No annotations are provided, so the description carries the full burden. It states the tool returns a complete record with specific fields, which is good, but does not explicitly mention read-only behavior or any side effects. For a simple read tool, this is adequate but could be improved.

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 sections for description, Args, Returns, and Tips. It is front-loaded with the purpose and is concise, but the Args and Returns sections could be integrated into the main description to reduce redundancy.

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

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

Given the tool has only two parameters, no output schema, and no annotations, the description provides sufficient information for a simple retrieval tool. It explains the purpose, parameters, and gives usage tips. It does not cover error handling, but that is acceptable for this straightforward 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 provides no parameter descriptions (0% coverage), but the description adds parameter meanings in the Args section: nhle_id as 'NHLE list entry number (e.g. '1002345')' and output_mode as 'Response format — 'json' (default) or 'text''. This compensates well for the missing schema details, though 'text' format is not further elaborated.

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 'Get full details for a specific scheduled monument.' The verb 'Get' and resource 'scheduled monument' are specific, and the tool is distinguished from siblings like search and other get tools by focusing on scheduled monuments.

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 'Tips for LLMs' section advises using nhle_id from search results, providing clear guidance. However, there is no explicit statement on when not to use the tool or alternatives, though the context of siblings implies this tool is for retrieving full records after search.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It explains the tool retrieves a single record and describes the return format and fields (site type, form, location, grid reference). It does not mention side effects or permissions, but these are likely minimal for a read-only lookup tool.

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

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

The description is concise and well-structured: a clear title sentence, followed by a brief explanation, labeled Args and Returns sections, and a practical tip for LLMs. Every sentence adds value with no redundancy.

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

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

The tool is simple with two parameters and no output schema, but the description explains return fields adequately. It could mention error handling or rate limits, but for a read-only lookup tool, the coverage is sufficient for correct usage.

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

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

Schema has 0% coverage with no descriptions for the two parameters. The description fully compensates by explaining record_id accepts two formats ('scotland:CANMOREID' or just the ID) and output_mode options ('json' default or 'text'), adding crucial meaning beyond the bare schema.

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

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

The description clearly states the verb 'get' and the resource 'Scottish NRHE record', specifying it retrieves full details by Canmore ID. It distinguishes from sibling tools like her_search_scotland by focusing on retrieval of a single record.

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

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

The description advises using record_id from her_search_scotland results, providing clear context for when to use this tool. However, it does not explicitly mention when not to use it or suggest 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively explains the return structure (metadata including query types, coverage area, status) and provides usage tips, though it could explicitly state it is a read-only operation.

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

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

The description is well-structured with sections for Args, Returns, and Tips. It front-loads the core purpose and adds valuable context without excessive verbosity.

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 (1 optional param, no output schema), the description is sufficiently complete. It explains what the tool returns and provides usage guidance, fulfilling the agent's needs for discovery.

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 explains the single parameter 'output_mode' as 'Response format — "json" (default) or "text"', adding meaning beyond the schema. With 0% schema coverage, this compensates well, though enum options are not formally defined.

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 'List all registered heritage data sources and their capabilities' with a specific verb and resource, distinguishing it from siblings that focus on searching, counting, or exporting specific data types.

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

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

Explicit tip 'Use this to discover which sources are available and what each one can do before running queries' provides clear context for when to use the tool, though it lacks explicit exclusion of 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 declare readOnlyHint=true, providing the core behavioral trait. The description adds context about multi-layer, color-coded output, which is beneficial but not critical 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 at two short sentences, front-loading the purpose without fluff. However, it could pack more parameter guidance without losing efficiency.

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 8 parameters, no required ones, and many sibling tools, the description lacks context on parameter usage, output details, and differentiation from similar mapping tools like 'her_crossref_map'.

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 and 8 parameters, the description provides no explanation for any parameter (lat, lon, bbox, etc.). This fails to compensate for the missing schema descriptions.

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

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

The description clearly states the verb 'visualise', the resource 'heritage assets from multiple sources', and the output 'a multi-layer interactive map' with color-coded layers. It distinguishes from sibling search and list 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 provides no explicit guidance on when to use this tool versus alternatives like 'her_nearby' or 'her_search_*'. No when-not or alternative scenarios are mentioned.

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 discloses that it searches NHLE, returns sorted by distance, and includes tips about coordinate systems and result details. It does not explicitly address permissions or side effects, but the read-only nature is implied. Slight lack of explicit non-destructive assertion.

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 sections for Args, Returns, and Tips. It is slightly lengthy but each sentence adds value. The main purpose is front-loaded, and the structure aids readability.

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

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

Given no output schema, the description adequately describes returns. It accounts for the complexity of 7 parameters with coordinate system choices and links to sibling tools. It provides comprehensive guidance for a complete search workflow.

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 0% description coverage, but the description provides extensive parameter documentation in the Args section, including coordinate alternatives, default values, and usage constraints (lat/lon vs easting/northing). This adds critical 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 clearly states the verb 'Find' and resource 'NHLE heritage assets near a single point'. It specifies the spatial search within a radius and sorting by distance. It also distinguishes from sibling tools by mentioning Scottish and aerial 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 description explicitly tells when to use this tool (for NHLE in England) and when not (use her_search_scotland for Scotland, her_search_aerial for aerial features). It also advises calling both for comprehensive results, providing clear alternatives and context.

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

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

No annotations are provided, so the description bears full responsibility. It explains the data source (AIM), return fields (monument type, period, evidence), and output formats, implying a safe read operation. It does not explicitly state read-only or disclose any side effects, which is acceptable for a search tool.

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

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

The description is well-structured with a clear intro, parameter list, return info, and LLM tips. It front-loads the purpose. While long, every sentence provides value for a complex tool with 9 parameters, though minor redundancy exists (e.g., repeating the data 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 search capability, parameters, return content, and cross-references to sibling tools. It lacks explicit pagination semantics (offset meaning, result limits) and error handling, but overall is quite complete for a search tool.

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

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

Schema description coverage is 0%, but the description provides detailed explanations for all 9 parameters, including examples, default values, and tips (e.g., 'monument_type: Monument type keyword (e.g. "SALTERN MOUND", "ENCLOSURE")'). This adds critical meaning beyond the raw 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 starts with a specific verb ('Search') and resource ('aerial investigation mapping data'), explicitly states it queries Historic England AIM data for archaeological features from aerial photos and LiDAR, and contrasts with NHLE monuments, distinguishing it from sibling tools like her_search_monuments.

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 tells when to use this tool (for cropmarks, earthworks, etc. not in NHLE), provides tips for LLMs on keyword usage, and recommends running all three sources (NHLE, AIM, Heritage Gateway) for comprehensive surveys, thus guiding on 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 full burden. It describes the search as querying a dataset and returning matches, but does not explicitly state side effects, limitations, or error handling. Since it's a read-only search, the lack of behavioral depth is acceptable but not exceptional.

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 sections for summary, args, returns, and tips. Though slightly lengthy due to parameter documentation, every sentence serves a purpose. The structure is clear and easy to scan.

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

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

Given 9 parameters, no output schema, and no annotations, the description covers all necessary context: purpose, dataset origin, parameter details, return format, and usage advice. It is complete for a search 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%, but the description provides detailed explanations for all 9 parameters, including expected formats (e.g., bbox as 'xmin,ymin,xmax,ymax' in BNG), defaults, and constraints (max_results 1-2000). This fully compensates for the empty 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 starts with 'Search conservation areas across England,' a specific verb+resource. It distinguishes from siblings by specifying the dataset (Historic England's Conservation Areas) and including tips that reference her_count_conservation_areas as 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 'Tips for LLMs' section explicitly tells when to use lpa, spatial parameters (bbox, lat/lon), and suggests using her_count_conservation_areas first to gauge result size. This provides clear usage guidance and alternative tool references.

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 for behavioral disclosure. It describes the operation as 'Search' and explains parameters and tips, but does not explicitly state that it is read-only or mention any limitations like data freshness or permissions. The lack of output schema also leaves some uncertainty about return 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?

The description is well-structured with sections for purpose, covered types, Args, Returns, and Tips. It is front-loaded with the primary purpose. While comprehensive, it could be slightly more concise by removing redundant phrasings, but overall it effectively organizes essential information for a tool with 10 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?

Given the complexity (10 parameters, no output schema, no annotations), the description covers all parameters, provides tips, and mentions that results include designation_type. However, it lacks explicit constraints on parameter combinations (e.g., radius search requires both lat and lon) and does not detail pagination behavior beyond the offset parameter. It is satisfactory 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?

The input schema has 0% description coverage, so the description must fully define parameters. It does so effectively in the Args section, explaining each parameter's purpose, format (e.g., bbox format, lat/lon for radius), and defaults (e.g., max_results default 50). It also lists possible values for designation_type, adding meaning beyond the schema's string type.

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 'Search across all designation types in the NHLE' and lists the specific types, providing a clear verb (Search) and resource (designation types). It distinguishes itself from sibling tools like her_search_listed_buildings by being a generic cross-type search.

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 tips section advises to leave designation_type empty to search all types and to use her_count_features first for quick totals, offering guidance on when to use and an alternative action. However, it does not explicitly state when not to use this tool (e.g., preferring dedicated search tools for a single type), so it lacks full exclusion criteria.

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

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

With no annotations provided, the description carries the full burden. It discloses that it queries an annual register and returns entries with category and risk methodology. It does not indicate any destructive behavior or rate limits, but for a search tool 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?

The description is well-structured with Args, Returns, and Tips sections, making it easy to navigate. It is fairly long but every sentence adds value, though minor redundancy exists (e.g., repeating query description).

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

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

Given 9 parameters, no output schema, and no annotations, the description covers all essential aspects: what the tool does, all parameters with clarifications, and return values. It could improve by specifying the output format for 'text' mode or adding examples.

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?

Despite 0% schema description coverage, the description provides detailed explanations for all 9 parameters, including allowed values for heritage_category and tips for spatial queries. This adds substantial meaning beyond the bare schema.

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

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

The description clearly states it searches the Heritage at Risk Register for endangered heritage assets. It uses a specific verb ('Search') and specific resource ('Heritage at Risk Register'), distinguishing it from sibling tools like her_get_heritage_at_risk (which likely gets a specific entry) or her_search_monuments.

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

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

The description provides explicit guidance in the 'Tips for LLMs' section, suggesting to use heritage_category and combine with spatial parameters. It also clarifies that these entries also appear in NHLE searches. However, it does not explicitly state when not to use this tool or mention 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?

With no annotations, the description carries full burden. It discloses 'Best-effort access via web scraping' and graceful empty results on unavailability. However, it does not cover rate limits, authentication, or further behavioral nuances, though the tool's read-only nature is implied.

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 description, Args, Returns, and Tips sections. It is concise with no redundant sentences, every line adds value—especially the critical tips about merging results and spatial filtering.

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

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

Given no output schema and no annotations, the description covers the tool's purpose, usage, parameter meanings, and fallback behavior. It could be more complete by specifying the return format or data structure, but the Returns line gives a general idea. The tips enhance completeness.

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

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

Schema coverage is 0%, but the description compensates with an Args section explaining each parameter (what, where, when, max_results, output_mode) and their default values. It adds context like 'Monument type or keyword' for 'what' and place name for 'where', but lacks format constraints or examples.

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

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

The description clearly states the tool searches local Historic Environment Records via Heritage Gateway, specifying it covers undesignated sites not in the NHLE. It distinguishes from sibling tools like her_search_monuments and her_search_aerial by mentioning alternative coverage.

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

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

Explicitly states when to use (best for undesignated sites and local HER data) and provides clear guidance on when not to rely solely on it, recommending to also run her_search_monuments and her_search_aerial. Includes spatial filtering tip using her_enrich_gateway.

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

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

With no annotations, the description carries the full burden. It states 'Queries the NHLE' and describes parameters and return format, implying a read-only search. However, it does not disclose quotas, rate limits, or side effects beyond the query 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 well-structured with a clear purpose sentence, then Args/Returns/Tips sections. Every sentence adds value; no unnecessary words. It is concise despite covering many 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?

Given 9 parameters, no output schema, and no annotations, the description is quite complete: all parameters documented, return format specified, and grading explained. Minor gap: the return structure ('Matching listed buildings with grade and location') could be more specific, but overall it's thorough.

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%, but the description provides rich parameter details: types, formats (e.g., 'xmin,ymin,xmax,ymax' for bbox), units, defaults, and constraints. This fully compensates for the missing schema descriptions.

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

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

The description clearly states 'Search listed buildings by location, name, or grade' with specific verb and resource. It distinguishes from sibling tools (e.g., her_search_aerial) by focusing on listed buildings and referencing the NHLE and grading system.

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

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

The description provides clear context for when to use (searching listed buildings) and includes tips for LLMs (e.g., grading hierarchy, using bbox/lat-lon). However, it does not explicitly mention when not to use or suggest alternatives among siblings.

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

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

With no annotations, the description carries the burden. It discloses that it queries NHLE, returns matching monuments with location and metadata, and implies it is a read operation (search). However, it does not explicitly state it is read-only or mention rate limits. Still, it adequately conveys the tool's behavior.

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

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

The description is well-structured with a concise summary, detailed Args list, Returns section, and Tips for LLMs. It is front-loaded with the purpose. Every sentence adds value without redundancy.

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

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

Given 9 parameters, no required ones, and no output schema, the description fully explains parameter usage, return value (matching monuments with location and metadata), and provides cross-references to sibling tools. It is comprehensive for an LLM to use correctly.

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

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

Schema coverage is 0%, so the description must compensate. It provides detailed explanations for all 9 parameters, including formats like 'bbox as xmin,ymin,xmax,ymax in BNG (EPSG:27700)', radius in metres, max_results range, and output_mode values. This adds significant meaning beyond the bare 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 'Search scheduled monuments by location, name, or description.' It specifies the resource (scheduled monuments) and the actions (search). It distinguishes from siblings by noting that NHLE only contains designated assets and suggests other tools for undesignated sites.

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

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

The description provides explicit when-to-use guidance for each parameter (bbox for area, lat/lon+radius for point, name for text). It includes tips for LLMs, such as following up with her_get_monument, using her_count_features first, and alternatives for undesignated sites. This clearly differentiates usage from sibling 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 provided, so description carries full burden. It discloses that it queries NRHE, covers terrestrial sites, and mentions MapServer max of 1,000 records per request. It also describes return format. However, it does not explicitly state that the tool is read-only or mention any authentication or rate limits.

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

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

The description is somewhat lengthy but well-structured with sections: summary, args, returns, tips. Every sentence adds value, though tips could be slightly condensed. The structure aids readability.

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

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

Given 10 parameters, no output schema, and many sibling tools, the description is highly complete. It covers all parameters, provides usage guidance, mentions limits, and cross-references related tools. The return description is brief but adequate.

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

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

Schema description coverage is 0%, and description compensates fully. Each parameter is explained with clear meaning (e.g., 'Site name keyword (partial, case-insensitive)'), examples for site_type, and format for bbox. It also explains usage constraints like lat/lon requiring radius_m.

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 searches Scottish NRHE records (320,000+ sites from Canmore). It specifies the resource (terrestrial archaeological sites, monuments, and buildings in Scotland) and distinguishes from sibling tools like her_search_scotland_designations.

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

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

Explicitly provides when-to-use guidance: mentions that for designated assets only, use her_search_scotland_designations, and for cross-border queries near England/Scotland border, also run her_search_monuments and her_search_aerial. Also includes tips for site_type keywords and max results limit.

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

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

No annotations provided, so description carries full burden. It describes return type, parameter constraints (e.g., bbox in BNG, radius requires lat/lon), and mentions default max_results. No contradictions, but could mention if there are any rate limits or pagination.

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?

Structured with a brief purpose, parameter list, returns, and tips. No redundant sentences; every part adds value. Front-loaded with the core functionality.

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 8 parameters, no output schema, and no annotations, the description provides thorough parameter explanations and usage context. However, it does not detail the exact structure of returned data beyond mentioning type, category, location.

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%, but the description fully explains each parameter, including defaults and valid values. However, the explanation is in text rather than in the schema; a more structured format could improve machine readability.

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

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

Clearly states the tool searches Scottish designated heritage assets and lists all covered types. Distinguishes from siblings like her_search_designations (English NHLE) and her_search_scotland (all Scottish sites) in the tips.

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

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

Explicitly advises when to use this tool versus her_search_scotland (for all sites) and recommends also searching English sources for cross-border queries. Provides clear context for selection.

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

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

No annotations exist, so description carries full burden. It correctly indicates a read-only operation (checking health) without mentioning any destructive or side effects. Could explicitly state it is non-destructive.

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?

Concise yet complete: introduction, args, returns, and usage tips. Every sentence adds value, 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?

Adequately covers the simple health check function with one optional parameter. Describes return content (version, statuses, tool count). Could be considered complete for its 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?

Only one parameter with 0% schema coverage. Description explains output_mode accepts 'json' (default) or 'text', adding meaning beyond the schema's basic type/default.

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 checks server health and data source availability, specifying it returns version, source statuses, and tool count. This distinguishes it from sibling tools that are search or retrieval focused.

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

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

Explicitly advises calling this first to check available sources, providing a clear use context. Lacks explicit when-not-to-use, but that's less critical for a health check tool.

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