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

With no annotations provided, the description carries full burden for behavioral disclosure. It states the action ('execute arbitrary Python code') but provides no information about security implications, execution environment, error handling, side effects, or what happens to Blender's state. For a code execution tool with zero annotation coverage, this is a significant gap in safety and behavior disclosure.

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 appropriately concise with two sentences that directly address purpose and parameters. The structure is clear with purpose first, then parameter documentation. There's no wasted text, though it could benefit from more context given the tool's complexity. Every sentence serves a functional 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?

For a code execution tool with no annotations, no output schema, and significant behavioral implications, the description is incomplete. It doesn't address critical context like execution safety, environment details, return values, error conditions, or how this integrates with Blender's state. The description provides only basic operational information without the necessary context for safe and 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?

The description explicitly documents the single parameter ('code: The Python code to execute'), adding meaning beyond the schema which has 0% description coverage. However, it provides minimal semantic context - no examples, no constraints on what code is valid, no mention of Blender API availability, or execution scope. The description compensates for the schema gap but only at a basic level.

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

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

The description clearly states the tool's purpose as 'Execute arbitrary Python code in Blender' - a specific verb ('execute') with resource ('Python code') and context ('in Blender'). It distinguishes itself from sibling tools which are all export/get/list operations focused on IFC data, making this the only code execution tool. However, it doesn't explicitly contrast with siblings beyond the inherent difference in function.

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 guidance on when to use this tool versus alternatives. While it's clearly different from all sibling tools (which handle IFC data export/query), there's no explicit when/when-not guidance, no mention of prerequisites, and no discussion of alternative approaches for similar functionality. The agent must infer usage context from the tool name alone.

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

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

With no annotations provided, the description carries the full burden and does well by detailing the multi-step conversion process, configuration file dependencies, and output behavior (creates a file in exports/ folder). It could improve by mentioning potential side effects like file overwriting or performance implications.

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

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

The description is front-loaded with the core purpose but includes extensive details (e.g., step-by-step conversion, features, configuration files) that, while informative, could be streamlined. Some sentences, like listing configuration file paths, may not all earn their place for an AI agent's tool selection.

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 complexity (multi-step conversion, external dependencies) and lack of annotations or output schema, the description is largely complete, covering process, features, configuration, parameters, and returns. It could be enhanced by clarifying error handling or input validation for the IFC model.

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 compensates by explaining the 'language' parameter's purpose ('Language for the budget file'), options ('es' for Spanish, 'en' for English), and default value ('Default is 'es''), adding 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 the specific action ('Export a BC3 budget file') and resource ('based on the IFC model loaded in Blender'), distinguishing it from sibling tools like export_ifc_data or get_ifc_quantities by focusing on budget generation rather than data extraction or 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?

The description implies usage context by specifying it works 'based on the IFC model loaded in Blender,' but does not explicitly state when to use this tool versus alternatives like export_ifc_data or generate_ids, nor does it mention prerequisites or 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?

With no annotations provided, the description carries full burden and does well by disclosing key behaviors: it creates a drawing (implies mutation/write operation), specifies default values and limits (e.g., 'max recommended 4096'), and describes output handling (file path vs base64). However, it lacks details on permissions, error conditions, or performance implications.

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

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

The description is appropriately sized and front-loaded with the core purpose. The parameter explanations are necessary given the 0% schema coverage, though the 'Returns' section could be integrated more smoothly. No redundant sentences.

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

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

For a 6-parameter tool with no annotations and no output schema, the description is quite complete: it covers purpose, parameters, and output behavior. It could improve by detailing error cases or performance constraints, but given the context, it provides sufficient guidance for effective tool use.

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

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

Schema description coverage is 0%, so the description must compensate fully. It provides detailed semantics for all 6 parameters: explains what each parameter controls (e.g., 'Height in meters above the storey level'), lists valid values for 'view_type', specifies defaults and limits, and clarifies optional behavior for 'storey_name' and 'output_path'.

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

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

The description clearly states the tool's purpose: 'Export drawings as PNG images with custom resolution.' It specifies the verb ('Export'), resource ('drawings'), and format ('PNG images'), and distinguishes it from sibling tools by focusing on visual export rather than data extraction or manipulation.

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 by mentioning 'architectural drawings' and IFC building context, but does not explicitly state when to use this tool versus alternatives like 'get_user_view' or 'execute_blender_code'. No exclusions or prerequisites are provided.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool 'extracts IFC data and creates a structured export file' and returns a confirmation or error message, but lacks critical details: whether this is a read-only operation, if it modifies source data, what permissions are required, file size limits, or performance characteristics. For a data export tool with zero annotation coverage, this is insufficient.

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 opening sentence, followed by elaboration, and then a formatted parameter section. It's appropriately sized at 7 sentences. The only minor inefficiency is repeating 'leave empty for all' twice instead of consolidating, but overall it's efficient and front-loaded.

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 moderate complexity (4 parameters, no annotations, no output schema), the description is minimally adequate. It covers the basic purpose and parameters but lacks behavioral context, error handling details, and output specifics beyond a vague 'confirmation message.' For a data export tool, more information about file location, format specifics, or limitations would be helpful.

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

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

The description adds significant value beyond the input schema, which has 0% description coverage. It explains all three user-facing parameters (entity_type, level_name, output_format) with examples and clarifies that empty values mean 'all entities' or 'all levels.' The 'ctx' parameter isn't mentioned, but this is acceptable as it appears to be a system parameter. The description compensates well for the schema's lack of documentation.

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

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

The description clearly states the tool's purpose: 'Export IFC data to a file in JSON or CSV format.' It specifies the verb ('export'), resource ('IFC data'), and output formats. However, it doesn't explicitly differentiate from sibling tools like 'export_bc3_budget' or 'export_drawing_png', which also export data but in different formats or contexts.

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 guidance on when to use this tool versus alternatives. It mentions filtering capabilities but doesn't compare to siblings like 'list_ifc_entities' or 'get_ifc_properties' that might retrieve similar data without exporting. There's no mention of prerequisites, dependencies, or typical use cases.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool creates a file (implying a write operation) and mentions the return format. However, it doesn't cover important behavioral aspects like error handling beyond the return structure, whether the operation is idempotent, what happens if the output_path already exists, or any performance/rate limit considerations. The description adds some value but leaves significant gaps for a file-creation 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 clear sections for parameters and returns. It's appropriately sized for a tool with 9 parameters. Every sentence adds value, though the parameter explanations could be slightly more concise. The information is front-loaded with the core purpose first.

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 (9 parameters, file creation operation, no annotations, no output schema), the description does a good job. It explains the purpose, documents all parameters semantically, and describes the return format. The main gaps are lack of usage guidelines and incomplete behavioral transparency (missing error scenarios, file overwrite behavior, etc.). For a tool with this parameter complexity, it's quite complete but not perfect.

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 compensates exceptionally well. It provides detailed semantic explanations for all 9 parameters: it explains what 'title' and 'specs' are (including the complex structure of specs with facet types), lists the 6 metadata parameters, and clarifies the behavior of 'output_path' (default naming if omitted). This goes far beyond what the bare schema provides.

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

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

The description clearly states the tool's purpose: 'Creates an .ids file in Blender/Bonsai by calling the add-on handler 'generate_ids''. It specifies the verb ('creates'), resource ('.ids file'), and context (Blender/Bonsai add-on). However, it doesn't explicitly differentiate this tool from its siblings (which are mostly IFC-related tools), though the '.ids file' creation is distinct enough in practice.

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 guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, dependencies, or scenarios where this tool is appropriate versus other tools in the server (like execute_blender_code or export functions). The only implicit usage hint is the Blender/Bonsai context, but no explicit when/when-not guidance is provided.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool creates/updates objects and optionally updates IfcSite and writes to disk, indicating it's a mutation/write operation. However, it lacks critical behavioral details: what permissions are needed, whether changes are reversible, what happens if the file isn't saved, error conditions, or performance characteristics. For a complex 23-parameter mutation tool, this is a significant gap.

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 appropriately concise at three sentences. It's front-loaded with the core purpose, followed by optional behaviors. No wasted words, though it could be slightly more structured (e.g., bullet points for optional features). Every sentence adds value: the first states the main action, the second adds optional site updates, and the third clarifies file writing.

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 high complexity (23 parameters, mutation operation), lack of annotations, 0% schema description coverage, and no output schema, the description is incomplete. It doesn't explain what the tool returns (success/failure, updated objects, file path), doesn't detail parameter interactions (e.g., how crs_mode affects other params), and omits error handling. For a tool of this complexity, the description should provide much more contextual guidance.

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

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

Schema description coverage is 0%, so the schema provides only parameter names and types without explanations. The description mentions 'crs_mode' (implied by 'creating or updating IfcProjectedCRS'), 'epsg' (implied by georeferencing), and 'write_path' (implied by 'writes the file to disk'), but doesn't explain the purpose, relationships, or constraints of the 23 parameters. It fails to compensate for the complete lack of schema descriptions, leaving most parameters semantically opaque.

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

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

The description clearly states the tool's purpose: 'Georeferences the IFC currently opened in Bonsai/BlenderBIM by creating or updating IfcProjectedCRS and IfcMapConversion.' It specifies the verb ('georeferences'), resource ('IFC'), and target objects (IfcProjectedCRS, IfcMapConversion). However, it doesn't explicitly differentiate from siblings like 'get_ifc_georeferencing_info' (which likely reads rather than writes georeferencing 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 minimal usage guidance. It mentions the tool operates on 'the IFC currently opened in Bonsai/BlenderBIM,' which implies a prerequisite (an open IFC file), but doesn't specify when to use this tool versus alternatives like 'get_ifc_georeferencing_info' (for reading) or other geospatial tools. No explicit when-not-to-use or alternative recommendations are provided.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it checks georeferencing status, returns structured JSON data, acts as a wrapper for a Blender add-on command, and always returns pretty-printed JSON. However, it doesn't mention performance characteristics, error handling, or prerequisites like whether an IFC file must be loaded.

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 clear sections (description, parameters, returns, notes) and front-loaded with the core purpose. Most sentences earn their place by explaining functionality, parameters, returns, or implementation details. The detailed return structure is necessary but makes it somewhat lengthy.

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 moderate complexity (1 parameter, no annotations, no output schema), the description is complete enough. It thoroughly documents the return format with detailed JSON structure, explains the parameter's effect, notes the wrapper implementation, and covers the tool's purpose. No output schema exists, so the detailed return documentation is essential and well-provided.

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

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

The description adds significant meaning beyond the input schema. The schema only shows 'include_contexts' as a boolean with 0% description coverage, while the description explains that this parameter adds 'a breakdown of the RepresentationContexts and operations' and shows exactly where this data appears in the output ('contexts' field only if true). This compensates well for the low schema 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 clearly states the tool's purpose with specific verbs ('checks', 'returns') and resources ('IFC currently opened in Bonsai/BlenderBIM', 'key georeferencing information'). It distinguishes itself from siblings like 'georeference_ifc_model' (which sets georeferencing) by focusing on information retrieval rather than modification.

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 when georeferencing information is needed, but doesn't explicitly state when to use this tool versus alternatives like 'get_ifc_project_info' or 'get_ifc_spatial_structure'. It mentions the tool acts as a wrapper for the Blender add-on, suggesting it's for querying georeferencing data specifically, but lacks explicit guidance on alternatives or 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the return format ('JSON-formatted string') but doesn't cover other critical aspects like whether this is a read-only operation, potential performance impacts, error conditions, or if it requires specific permissions. For a tool with zero annotation coverage, this is inadequate.

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 two sentences: one stating the purpose and one specifying the return format. It's front-loaded with the core functionality, though the second sentence could be integrated more smoothly.

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 (0 parameters, no output schema), the description is minimally adequate. It covers what the tool does and the return format, but lacks details on usage context, behavioral traits, or error handling. With no annotations and multiple sibling tools, it should provide more guidance to be fully complete.

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

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

The tool has 0 parameters, and the input schema has 100% description coverage (though empty). The description doesn't need to add parameter details, so it meets the baseline expectation. No extra value is added, but none is required.

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

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

The description clearly states the tool's purpose: 'Get basic information about the IFC project, including name, description, and counts of different entity types.' This specifies the verb ('Get'), resource ('IFC project'), and scope ('basic information'), though it doesn't explicitly differentiate from sibling tools like 'get_ifc_georeferencing_info' or 'get_ifc_properties'.

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 guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, context, or exclusions, and with multiple sibling tools that also retrieve IFC data (e.g., 'get_ifc_georeferencing_info', 'get_ifc_properties'), the lack of differentiation is a significant gap.

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 the tool's dual behavior modes and output format (JSON-formatted string), but lacks details on permissions, rate limits, error conditions, or whether it's read-only (implied by 'Get' but not explicit). It adequately describes what the tool does but misses some behavioral traits.

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

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

The description is front-loaded with the core purpose, followed by clear sections for Args and Returns. Every sentence earns its place: no redundancy, and the structure (purpose, parameters, return) is logical and efficient for quick understanding.

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 2 parameters with 0% schema coverage and no output schema, the description provides adequate basics (purpose, parameters, return format) but lacks depth. It doesn't explain the JSON structure, error handling, or dependencies (e.g., Blender context), leaving gaps for a tool with moderate complexity and no annotations.

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

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

The schema description coverage is 0%, so the description must compensate. It adds meaningful semantics: explaining that global_id is optional when selected_only is True, clarifying that selected_only returns properties for all selected objects, and indicating the mutual exclusivity between the two parameters. This goes beyond the bare schema, though it could detail parameter formats or constraints more.

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

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

The description clearly states the verb 'Get' and resource 'properties of IFC entities', specifying two distinct modes: by GlobalId or for selected Blender objects. It distinguishes itself from siblings like 'get_ifc_quantities' or 'get_ifc_relationships' by focusing on properties rather than other entity attributes.

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 each mode (by GlobalId vs. selected objects) and mentions the optional nature of global_id when selected_only is True. However, it doesn't explicitly state when to choose this tool over similar siblings like 'get_selected_ifc_entities' or 'list_ifc_entities', which might offer overlapping functionality.

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 mentions the return format ('JSON-formatted string') but doesn't disclose behavioral traits like whether this is a read-only operation, potential performance impacts, or any prerequisites. For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves.

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 brief and front-loaded with the core purpose in the first sentence. The second sentence about return format is useful but could be integrated more smoothly. Overall, it's efficient with minimal waste, though slightly fragmented.

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 annotations and no output schema, the description is incomplete. It doesn't explain what 'basic qtos' includes, how the data is structured, or any limitations. For a data retrieval tool in a context with many similar siblings, more detail is needed to ensure proper 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?

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the lack of inputs. The description adds no parameter information, which is appropriate here. Baseline is 4 for zero parameters, as no compensation is needed.

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 the tool 'Extract and get basic qtos about the IFC project' which provides a general purpose (extract quantities) but lacks specificity. It doesn't clearly distinguish from siblings like 'get_ifc_project_info' or 'get_ifc_properties', making it somewhat vague about what exactly 'qtos' (quantities) entails compared to other data retrieval 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?

No guidance is provided on when to use this tool versus alternatives. With siblings like 'get_ifc_project_info' and 'get_ifc_properties' that might retrieve overlapping or related data, the description offers no context about when this specific quantity extraction is appropriate, leaving usage decisions unclear.

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 of behavioral disclosure. It states the tool retrieves relationships but lacks details on permissions, rate limits, error handling, or data format specifics beyond 'JSON-formatted string.' For a read operation with no annotation coverage, this is insufficient to fully understand its behavior and 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 highly concise and well-structured: a clear purpose statement followed by brief 'Args' and 'Returns' sections. Every sentence adds value without redundancy, making it easy to scan and understand quickly. This efficient formatting enhances usability.

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, no annotations), the description is minimally complete. It covers the basic purpose and parameter semantics but lacks output details (e.g., structure of the JSON) and behavioral context. For a straightforward read tool, this is adequate but leaves gaps in full understanding.

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

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

The description adds meaningful context for the single parameter 'global_id' by explaining it is the 'GlobalId of the IFC entity,' which clarifies its purpose beyond the schema's minimal title 'Global Id.' With 0% schema description coverage and only one parameter, this compensation is adequate, though not exhaustive (e.g., no format 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's purpose: 'Get all relationships for a specific IFC entity.' It uses a specific verb ('Get') and resource ('relationships'), but does not explicitly distinguish it from sibling tools like 'get_ifc_properties' or 'get_ifc_quantities', which might retrieve different types of entity data. This makes it clear but not fully differentiated from 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 provides no guidance on when to use this tool versus alternatives. It does not mention sibling tools such as 'get_ifc_properties' or 'get_ifc_spatial_structure', which might be used for related queries about IFC entities. Without this context, users must infer usage based on the tool name alone, leading to potential confusion.

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 states the return format ('JSON-formatted string') and the hierarchical scope, but it lacks details on permissions, rate limits, error handling, or whether this is a read-only operation (implied by 'Get' but not explicit). For a tool with zero annotation coverage, this is insufficient.

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

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

The description is front-loaded with the core purpose in the first sentence and adds a concise 'Returns' section. Every sentence earns its place by clarifying the output format without redundancy, making it highly efficient and well-structured.

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

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

Given the complexity (hierarchical data retrieval), no annotations, and no output schema, the description is minimally adequate. It explains what the tool does and the return format, but it lacks details on the JSON structure, error cases, or dependencies. This meets the minimum viable threshold but has clear gaps for a tool with no structured support.

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 parameters with 100% coverage, so the schema fully documents the lack of inputs. The description adds no parameter information, which is appropriate here. A baseline of 4 is given since no parameters exist, and the description doesn't need to compensate for any gaps.

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

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

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('spatial structure of the IFC model'), and it distinguishes the hierarchical focus from siblings like 'get_ifc_total_structure' or 'get_ifc_relationships'. However, it doesn't explicitly differentiate from 'list_ifc_entities' or 'get_selected_ifc_entities', which might also involve spatial elements, preventing a perfect 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 description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context (e.g., after loading a model), or comparisons to siblings like 'get_ifc_total_structure' for broader data or 'list_ifc_entities' for flat lists. This leaves the agent without explicit usage direction.

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 describes what the tool returns (JSON-formatted string with hierarchical structure and summary statistics) and its scope (spatial elements and building elements). However, it does not cover potential behavioral traits like performance implications, error conditions, or data size limitations that might be relevant for a comprehensive structure 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 and appropriately sized. It starts with a clear purpose statement, elaborates on what the tool extends and includes, and ends with return details. Each sentence adds value without redundancy. It could be slightly more concise by combining some clauses, but overall it is efficient and front-loaded.

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 complexity (comprehensive IFC structure) and lack of annotations and output schema, the description does a good job of covering key aspects: purpose, scope, return format, and differentiation from basic tools. It provides enough context for an agent to understand what the tool does and when to use it, though it could benefit from more behavioral details like performance notes.

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

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

The tool has 0 parameters, and schema description coverage is 100%. With no parameters to document, the description appropriately focuses on output semantics. It adds value by explaining what the return data includes (hierarchical structure, building elements, summary statistics) and the format (JSON-formatted string), which compensates for the lack of an output 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 purpose: 'Get the complete IFC structure including spatial hierarchy and all building elements.' It specifies the verb ('Get'), resource ('complete IFC structure'), and distinguishes from sibling tools like 'get_ifc_spatial_structure' by emphasizing inclusion of building elements. The description explicitly contrasts with the basic spatial structure, making the differentiation clear.

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

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

The description provides clear context for when to use this tool: it 'extends the basic spatial structure' and is for obtaining a 'comprehensive view' of the building organization. It implies an alternative (the basic spatial structure tool) but does not explicitly name it or provide exclusion criteria. The guidance is sufficient to understand the tool's role but lacks explicit when-not-to-use instructions.

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

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

With no annotations provided, the description carries the full burden. It discloses that the tool retrieves data (implied read-only) and specifies the return format ('JSON-formatted string'), but lacks details on permissions, error handling, or rate limits, which are important for a tool interacting with Blender selections.

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

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

The description is front-loaded with the core purpose in the first sentence, followed by usage context and return format in two additional sentences. Every sentence adds value without redundancy, making it efficiently structured and easy to parse.

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

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

Given the tool's moderate complexity (interfacing with Blender selections and IFC data), no annotations, and no output schema, the description is adequate but incomplete. It explains what the tool does and the return format, but lacks details on output structure, error cases, or prerequisites like Blender being in a specific state.

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 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately does not discuss parameters, focusing instead on the tool's purpose and output, which aligns with the baseline expectation for zero-parameter tools.

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 specific action ('Get IFC entities') and the target resource ('currently selected objects in Blender'), distinguishing it from siblings like 'list_ifc_entities' or 'get_ifc_properties' by focusing on user-selected objects rather than all entities or specific properties.

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

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

It provides clear context for when to use this tool ('working specifically with objects the user has manually selected in the Blender UI'), but does not explicitly mention when not to use it or name alternatives like 'list_ifc_entities' for non-selected objects.

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

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

With no annotations provided, the description carries full burden. It discloses the tool captures the viewport as an image and mentions focusing on the 3D viewport with UI assistance only when prompted. However, it doesn't describe error conditions, performance characteristics, or what happens if Blender isn't in a viewport state.

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 purpose statement, usage context, parameter details, and return value. Every sentence adds value: the first states the core function, the second clarifies scope, the third provides UI guidance, and the parameter/return sections document behavior.

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 annotations, no output schema, and 0 parameters in the schema, the description does well by explaining what it captures, how to use it, and documenting two important parameters. It could be more complete by describing the image format or error cases, but it covers the essentials adequately.

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

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

The input schema has 0 parameters with 100% coverage, so the baseline is 4. The description includes an 'Args' section with two parameters (max_dimension, compression_quality) that aren't in the schema, adding value beyond the structured data by documenting these optional parameters.

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

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

The description clearly states the tool's purpose: 'Capture and return the current Blender viewport as an image' with specific verb ('capture and return') and resource ('current Blender viewport'). It distinguishes from siblings by focusing on the visual viewport rather than IFC data, code execution, or exports.

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: 'Shows what the user is currently seeing in Blender' and 'Focus mostly on the 3D viewport.' It gives guidance on when to use it (for viewport capture) but doesn't explicitly state when not to use it or name specific alternatives among the 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the tool lists entities and can filter by selection, but doesn't disclose critical behavioral traits such as whether this is a read-only operation, potential performance impacts, rate limits, authentication needs, or what happens with null entity_type. The description is minimal and lacks depth for a tool with parameters.

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 appropriately sized. It starts with a clear purpose statement, followed by an Args section detailing each parameter with brief explanations, and a Returns section. Every sentence earns its place with no redundant information, making it easy to scan and understand quickly.

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

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

Given the tool's moderate complexity (3 parameters, no annotations, no output schema), the description is partially complete. It covers the purpose and parameters well but lacks behavioral context (e.g., read-only nature, error handling) and doesn't detail the return format beyond 'A JSON-formatted string,' which is insufficient without an output schema. For a listing tool with filtering options, more behavioral transparency would be beneficial.

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

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

The description adds significant meaning beyond the input schema, which has 0% schema description coverage. It explains all three parameters: entity_type ('Type of IFC entity to list'), limit ('Maximum number of entities to return'), and selected_only ('If True, only return information about selected objects'). This fully compensates for the schema's lack of descriptions, providing clear semantic context for each parameter.

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

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

The description clearly states the tool's purpose: 'List IFC entities of a specific type' with filtering options. It specifies the verb ('List') and resource ('IFC entities'), distinguishing it from siblings like 'get_selected_ifc_entities' by mentioning selection filtering as an option rather than the primary function. However, it doesn't explicitly differentiate from other listing tools like 'get_ifc_spatial_structure' or 'get_ifc_total_structure'.

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 context by mentioning 'Can be filtered to only include objects currently selected in the Blender UI,' which suggests when to use the selected_only parameter. However, it doesn't provide explicit guidance on when to choose this tool over similar siblings like 'get_selected_ifc_entities' or other get_ifc_* tools, nor does it mention prerequisites or 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes a write operation ('create and position IFC elements'), which implies mutation, but doesn't address critical behavioral aspects like permissions required, whether the operation is reversible, potential side effects on the model, or error handling. The return value description ('A message with the result') is vague about success/failure indicators.

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 appropriately sized. It begins with a clear purpose statement, followed by elaboration, then provides a formatted parameter section with clear documentation. While efficient, the 'Returns' section could be more specific about what the message contains, but overall the structure is logical and front-loaded.

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 this is a mutation tool with no annotations and no output schema, the description is moderately complete. It adequately explains the core functionality and parameters but lacks important contextual information about behavioral traits, error conditions, and the structure of return values. The description covers the 'what' but insufficiently addresses the 'how' and 'what happens after' aspects.

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

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

The description provides excellent parameter semantics beyond the input schema. With 0% schema description coverage, the description fully documents all 4 required parameters (type_name, x, y, z) and the optional rotation parameter, explaining what each represents, their data types, and default values. The 'ctx' parameter is not mentioned, but this appears to be an internal context parameter, so the description effectively covers all user-facing parameters.

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

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

The description clearly states the tool's purpose: 'Place an IFC object at a specified location with optional rotation.' It specifies the verb ('place'), resource ('IFC object'), and key actions (positioning with coordinates and rotation). However, it doesn't explicitly distinguish this from potential sibling tools like 'get_selected_ifc_entities' or 'list_ifc_entities', which are read operations versus this write operation.

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 minimal usage guidance. It states that the object type 'must exist in the model,' which is a prerequisite, but offers no explicit guidance on when to use this tool versus alternatives. There's no mention of when not to use it or what other tools might be more appropriate for related tasks.

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