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

With no annotations, the description carries full responsibility for behavioral disclosure, but it does not mention side effects, whether objects are modified in place or new objects are created, or any requirements like existing geometry. This lacks transparency for a mutation-like 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 concise and front-loaded with the main purpose. The parameter summary is useful and not verbose. It could be slightly better organized but is appropriately sized.

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 4 parameters, no schema descriptions, and no annotations, the description is under-specified. It lacks details on result_name, the exact behavior of the operation, and prerequisites or side effects. The presence of an output schema helps, but the description still leaves significant gaps.

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

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

The description partially compensates for the 0% schema coverage by explaining the operation values (fuse|cut|common) and that base_object/tool_objects accept entry IDs or names. However, it omits the result_name parameter entirely and does not clarify the array format of tool_objects, so the compensation is incomplete.

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 performs boolean operations on GEOM objects, naming the specific operations (fuse, cut, common). It distinguishes the general purpose from the more specific sibling tools, though it does not explicitly refer to them.

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 generic boolean_operation tool versus the dedicated fuse_objects, cut_objects, or common_objects tools. The description implies it can handle any of the three operations but doesn't advise on choice.

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 the returned data fields, indicating a read-only status check with no side effects. However, it does not mention error behavior, required permissions, or what happens when the bridge is unreachable, leaving some transparency gaps.

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 concise sentences, front-loaded with the core purpose, and every sentence adds value. It avoids fluff and clearly lists the expected return items.

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, parameterless health-check tool with an output schema, the description covers the essential return fields and notes 'when available' for study metadata, handling variability. It could add a use-case hint (e.g., initial connectivity check), but overall it is sufficiently complete given the tool's simplicity.

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

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

The tool has zero parameters, and the schema is empty with 100% coverage. The description appropriately avoids parameter details since none exist. The baseline for zero parameters is 4, and the description adds no unnecessary param information.

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 performs a 'standard health check' for bridge accessibility and active study, listing specific return fields (host/port, reachability, ping message, study metadata). It provides a clear verb and resource, and while it doesn't explicitly differentiate from sibling tools like ping_salome or get_study_info, the scope is evident from the combined output.

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

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

The description gives no explicit guidance on when to use this tool versus alternatives such as ping_salome or get_study_info. It only says 'standard health check', which implies general use but lacks clear context 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 must carry the full burden of behavioral disclosure. It does not state whether input objects are modified, whether a new object is created, what happens with an empty intersection, or what the output schema contains. The terse description leaves significant behavioral ambiguity.

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

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

A single, tightly worded sentence with no filler. The operation is front-loaded, and the parenthetical 'common region' adds useful clarification without unnecessary 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?

Despite having an output schema, the description lacks essential context: no usage guidance, no parameter semantics, and no behavioral transparency. Among many sibling tools, this description is too sparse to reliably guide selection and correct invocation.

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

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

Schema description coverage is 0%, and the description does not clarify the roles of base_object, tool_objects, or result_name. While 'Intersect GEOM objects' gives a general sense, it does not explain how the parameters relate to the operation or what result_name controls, leaving parameter semantics to inference.

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

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

The description states a specific verb ('Intersect') and resource ('GEOM objects'), and clarifies the result as a 'common region'. This distinguishes it from sibling tools like fuse_objects and cut_objects, though it does not explicitly differentiate from the more general boolean_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 implies usage: use this tool when you need the intersection/common region of GEOM objects. However, it provides no explicit guidance on when to prefer this over boolean_operation, fuse_objects, or cut_objects, and no exclusions or alternatives 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?

With no annotations provided, the description must disclose behavioral traits (e.g., side effects, read-only nature). The description does not indicate whether computation mutates any state, requires specific permissions, or modifies the mesh. 'Compute' is ambiguous and could imply creation or modification, making the lack of disclosure 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 a single sentence with no fluff, which is brief, but it is under-specified to the point of being unhelpful. Conciseness is appropriate when it is both short and informative; here it fails to convey essential meaning, making it underspecified rather than concise.

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

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

Despite having only one parameter, the description omits critical context: what mesh_ref refers to, whether the operation is read-only, what 'basic statistics' includes, and how it relates to other tools. Even if output schema covers return values, the lack of context about the input and side effects makes the tool description severely incomplete.

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

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

The schema has one required parameter, mesh_ref, with no description coverage. The tool description does not mention the parameter at all, so the agent cannot infer what 'mesh_ref' refers to (e.g., an existing mesh ID, a geometry reference, or a path). The description adds no value to the schema.

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

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

The description states an action, 'compute mesh', and an outcome, 'return basic mesh statistics'. However, the verb 'compute' is ambiguous—it could mean generating a mesh or analyzing an existing one. This ambiguity is not resolved by the parameter 'mesh_ref', and the tool is not clearly distinguished from siblings like create_mesh or get_mesh_info.

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 such as get_mesh_info or create_mesh. There is no mention of prerequisites, context, or exclusions, leaving the agent without a basis for selecting this 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 must carry the burden of behavioral disclosure. It only says 'copy,' implying a non-destructive action, but does not explain any side effects, requirements, or what happens to the source object. This is insufficient for a tool that creates new objects.

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

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

The description is a single short sentence with no unnecessary words, making it very concise and front-loaded. It gains no extra benefit from structure but is appropriately sized for the limited content it presents.

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 presence of similar sibling tools and an output schema, the description is too terse. It does not explain the return behavior, how this copy differs from other copy operations, or what a 'GEOM copy' entails, leaving significant contextual gaps.

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

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

The description gives no parameter information. With 0% schema description coverage, it fails to explain that 'source_ref' is the object to copy and what 'name' controls, leaving the agent to infer essential details from the schema alone.

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 creates a GEOM copy of an object, using the verb 'Create' and the resource 'GEOM copy.' However, it does not distinguish this from the sibling 'duplicate_object,' which likely performs a similar operation, so its uniqueness is unclear.

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. There is no mention of use cases, prerequisites, or when to avoid it, leaving the agent without context for tool 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?

With no annotations available, the description carries sole responsibility for behavioral disclosure. It only states 'Create' without mentioning side effects, return values, or how the box integrates with the study environment, leaving significant behavioral ambiguity.

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

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

The description is a single, concise sentence that immediately communicates the core action without extraneous information. It is well-structured and front-loaded, making it easy for an agent to quickly understand the tool's purpose.

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

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

For a tool with no annotations, no parameter descriptions, and just a minimal sentence, the overall description is incomplete. It lacks essential context about how the box is represented, what the output contains, and any dependencies or side effects, making it insufficient for an agent to fully 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?

Schema description coverage is 0%, so the description must compensate for parameter clarity. The phrase 'by dimensions' hints that dx, dy, dz relate to dimensions, but it does not explicitly map each parameter (e.g., length, width, height) or specify units, leaving the schema's bare numeric fields inadequately explained.

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

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

The description clearly states the tool's function as creating a GEOM box using dimensions, with a specific verb ('Create') and resource ('GEOM box'). It effectively distinguishes itself from sibling shape-creation tools like create_cylinder and create_sphere by focusing on box creation via dimensions.

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

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

No usage guidance is provided regarding when to use this tool compared to alternatives such as create_cylinder or create_sphere. There are no explicit exclusions or contextual cues beyond the obvious purpose of creating a box.

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, but it only states the creation action and position. It does not disclose side effects, required permissions, or behavior beyond the basic 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 under-specified at one sentence, lacking vital information about parameters and usage context, which makes it more under-specification than effective conciseness.

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 creation tool, the description omits details about naming defaults, units, and the object's role in the study, which the schema does not fully clarify. Given the absence of annotations, this leaves gaps in what an agent needs to know.

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

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

Schema description coverage is 0%, and the description does not mention any of the parameters (radius, height, name), so it adds no semantic meaning beyond the schema parameter names.

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 creates a GEOM cylinder at the origin, using a specific verb and resource, and distinguishes it from sibling tools like create_box and create_sphere.

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, nor any prerequisites or exclusions. It merely states the action without contextual selection 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, the description carries the full burden of behavioral disclosure. It only states that a group is created, but fails to mention side effects (like adding an object to the study), prerequisites (valid shape_ref and subshape_type), or failure behavior. This is insufficient for a mutating 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 a single, front-loaded sentence with no wasted words. It efficiently communicates the core action and method, exemplifying appropriate conciseness.

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 4 parameters, an output schema, and multiple closely related sibling tools, the description is far too sparse to be complete. It doesn't explain the meaning of shape_ref and subshape_type, nor does it clarify the difference between this and create_surface_group/create_volume_group, leaving significant gaps 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 description coverage is 0%, so the description must add meaning. It only clarifies subshape_ids ('from subshape IDs') while leaving shape_ref, subshape_type, and name unexplained. The property names and types in the schema are not enough to understand how to populate these fields correctly.

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 action ('Create'), the resource ('GEOM group'), and the method ('from subshape IDs'), making it specific and actionable. However, it doesn't differentiate this tool from closely related sibling tools like create_groups, create_surface_group, or create_volume_group, 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?

There is no guidance on when to use this tool versus alternatives, no mention of prerequisites, and no exclusions. The description simply states the action without explaining the context in which this tool is the right choice over its 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?

No annotations are provided, so the description must disclose behavioral traits. It only says 'create', which implies mutation, but does not mention potential side effects such as the 'replace_existing' parameter overwriting existing groups, or any requirements like shape_ref validity. This lack of detail leaves significant behavioral ambiguity for a mutation 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 extremely concise with exactly two sentences: one stating the purpose and one listing supported group item fields. Every sentence adds value, there is no fluff, and the purpose is front-loaded. This is an example of zero-waste structure.

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

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

Despite having an output schema, the description is incomplete for the tool's complexity. It omits key parameters like 'replace_existing' and does not explain the role of 'shape_ref'. While the group item fields are mentioned, the overall context is sparse, leaving the agent uncertain about how to properly invoke the tool beyond the most basic use.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaning by listing the supported keys for each group item (name, subshape_type, subshape_ids), but it does not explain 'shape_ref' or 'replace_existing', which are present in the schema. This partial compensation warrants a score above zero but below full 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 creates multiple GEOM groups in a single call, using the specific verb 'create' and the resource 'GEOM groups'. This distinguishes it from the sibling tool 'create_group' by highlighting the batch nature, satisfying the requirement for a specific verb+resource that distinguishes from siblings.

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

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

The phrase 'in one call' provides clear context for when to use this tool: when creating multiple groups is desired, as opposed to calling the singular 'create_group' multiple times. It implies efficiency but does not explicitly name alternatives or exclusions, which aligns with 'clear context, no 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 must disclose behavioral traits. It states the tool creates a mesh definition, but does not explain whether it modifies the GEOM object, whether it requires prerequisites, whether it replaces existing meshes, or what the side effects are. 'Standard hypotheses' is also vague.

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 very concise, with just two sentences. It front-loads the main purpose and includes a compact parameter list. However, the parameter list is presented as a simple enumeration without context, and the structure could be improved with clearer headings or formatting.

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

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

Despite having an output schema, the description is incomplete for a tool with 7 parameters, especially considering sibling tools like create_mesh_with_hypotheses and compute_mesh. It does not clarify what 'standard hypotheses' means, how parameters interact, or what the resulting mesh definition entails.

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

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

Schema description coverage is 0%, so the description must compensate. It lists allowed values for surface_algorithm and volume_algorithm, but provides no explanation for the other five parameters (mesh_name, shape_ref, segment_count, max_element_area, max_element_volume). This partial coverage is insufficient for a 7-parameter tool.

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 a specific action ('Create a mesh definition on GEOM object') and identifies the resource (GEOM object). It distinguishes from 'compute_mesh' but does not differentiate from sibling 'create_mesh_with_hypotheses', so it lacks full sibling differentiation.

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

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

There is no explicit guidance on when to use this tool versus alternatives. The phrase 'using standard hypotheses' vaguely implies a contrast with a custom-hypotheses tool, but no concrete when-to-use or when-not-to-use instructions are provided.

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

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

With no annotations, the description carries full behavioral disclosure burden, but it fails to mention important traits such as whether the mesh is immediately computed (given the 'compute' flag), side effects on the study, or requirements. The description only lists parameters without explaining behavioral consequences.

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 one-sentence purpose, followed by clear lists of algorithm values and hypotheses keys. Every entry adds value, with no redundant filler.

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

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

For a 5-parameter tool with no annotations, the description omits critical context such as the effect of the 'compute' flag, how the mesh creates objects in the study, and the relationship to the simpler create_mesh tool. The parameter lists help, but the overall operational context is incomplete.

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?

Although schema description coverage is 0%, the description compensates by enumerating supported algorithm values and common hypotheses keys, adding real semantics beyond the schema's bare types. However, it does not explain 'compute', 'mesh_name', or 'shape_ref', which remain underspecified.

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 action ('Create mesh with explicit algorithm and detailed hypotheses'), identifying a specific verb and resource. However, it does not explicitly distinguish this tool from the sibling 'create_mesh' or 'compute_mesh', so it lacks full sibling differentiation.

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

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

No guidance is provided on when to use this tool versus alternatives like create_mesh or compute_mesh. The description focuses entirely on parameter values rather than usage context 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, the description carries the burden of explaining behavior. It discloses the span-dependent 2D/3D output, which is valuable. However, it doesn't mention other behavioral aspects like how the shape integrates into the study or what the output object is, leaving some gaps.

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

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

The description is a single sentence that efficiently communicates the core function and the key parameter behavior. There is no unnecessary verbosity or repetition of schema details.

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 has an output schema, so return-value details are not required in the description. The description captures the main functional behavior (2D vs 3D) and is sufficient for a creation tool with straightforward parameters and sibling context.

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 descriptions (0% coverage), and the description only clarifies the 'span' parameter's effect. Other parameters like 'code', 'chord', and 'closed_te' are left to inference. This partial compensation is adequate but not comprehensive.

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 'Create a NACA 4-digit airfoil' with a specific verb and resource, distinguishing it from sibling tools like create_box or create_cylinder. It also adds the important 3D/2D distinction based on span, making the purpose 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?

The description implies the tool is for creating NACA airfoils, which is distinct from other shape tools. It doesn't explicitly mention when not to use it, but the context is clear enough for an agent to select it when an airfoil geometry is needed.

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 for behavioral transparency. It adds 'at origin' as a positional constraint, which is useful, but it does not disclose side effects such as whether the sphere is added to the current study, or any validation or return behavior. This is minimal but not misleading.

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

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

The description is a single, front-loaded sentence with no wasted words. It states the essential action and location, making it highly readable and scannable.

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 creation tool with only two parameters and an output schema, the description is minimally adequate. It covers purpose and placement, but lacks usage guidance and parameter context. The existence of an output schema reduces the need to explain return values, so a 3 is appropriate.

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

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

Schema description coverage is 0%, and the description does not mention the 'radius' or 'name' parameters at all. The agent must rely solely on the schema titles, which lack units, constraints, or any additional meaning. The description provides no compensation for the missing parameter descriptions.

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

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

Clearly identifies the action (create), the resource (GEOM sphere), and the placement (at origin). This distinguishes it from sibling shape-creation tools like create_box and create_cylinder, which target different shapes.

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

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

Usage is implied by the tool name and description: use when a sphere is needed. However, there is no explicit guidance on when to choose this over alternatives like create_box or create_cylinder, nor any 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?

There are no annotations, and the description itself fails to disclose any behavioral details. It does not mention side effects, requirements, error behavior, or what the wrapper actually does differently from a standard group creation.

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 extremely brief, but this is under-specification rather than effective conciseness. A single vague sentence does not earn its place as it omits critical details.

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

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

Despite having an output schema, the tool has meaningful complexity (grouping faces via shape references and subshape IDs) and no annotations. The description lacks essential context for correct selection and invocation, making it nearly unusable for an agent.

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

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

Schema description coverage is 0%, and the description provides no explanation of shape_ref, subshape_ids, or name parameters. The description adds no meaning beyond the schema field names.

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 'Create FACE group convenience wrapper,' which clearly identifies the action (create) and the resource type (FACE group), but the term 'convenience wrapper' is vague and does not differentiate it from sibling tools like create_group, create_groups, or create_volume_group.

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 such as create_group or create_volume_group. The description gives no context for selection criteria or prerequisites.

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

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

With no annotations, the description must convey behavioral traits, but it only says 'Create', implying a mutation. No side effects, required scope, or wrapper behavior details are provided.

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 extremely brief but under-specified, not concise. It fails to convey any useful information, similar to a tautology.

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

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

Despite having an output schema, the tool has 3 parameters and no annotations. The description is inadequate for an agent to select and invoke the tool correctly, leaving the purpose, usage, and parameters unclear.

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

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

Schema description coverage is 0%, and the description mentions none of the parameters (name, shape_ref, subshape_ids). It adds no meaning beyond the parameter names and types.

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 'Create SOLID group convenience wrapper' uses a vague verb+object but fails to clearly state that it creates a volume group. It doesn't explain what a 'SOLID group' is, nor does it distinguish from sibling tools like create_group, create_groups, or create_surface_group.

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 given on when to use this tool versus alternative group creation tools. There is no mention of prerequisites, context, 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 must disclose behavioral traits. It only states the operation without explaining side effects (e.g., whether the base object is modified or a new object is created), required preconditions, or how the result is stored. This is a significant gap for a geometry mutation 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 a single short sentence with no redundancy. It is easy to parse and appropriately sized for a simple operation.

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?

Even though an output schema exists, the description lacks essential context about the operation's behavior, prerequisites, and how inputs relate to outputs. With no annotations, the tool is under-specified and leaves too much to inference.

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

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

The schema has 0% parameter descriptions. The description adds meaning for base_object and tool_objects via 'base minus tools', but leaves result_name completely unexplained. It only partially compensates for the absent schema documentation.

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

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

The description clearly states the operation ('Cut'), the resource ('GEOM objects'), and the exact semantics ('base minus tools'). This directly distinguishes it from sibling tools like fuse_objects (union) and common_objects (intersection).

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

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

The phrase 'base minus tools' implies the use case for subtracting one object from another, but the description does not explicitly state when to choose this over boolean_operation or other siblings, nor does it mention any exclusions or prerequisites.

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

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. While 'Delete' implies a destructive operation, it does not mention irreversibility, behavior with child objects, or any side effects on the study or geometry. The with_children parameter is entirely ignored.

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

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

The description is a single, front-loaded sentence with no unnecessary words. It efficiently states the core purpose, though its extreme brevity does sacrifice necessary detail. This is genuine conciseness rather than padding.

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

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

Given the destructive nature of the tool, the presence of a boolean parameter with_children, and the lack of annotations, the description is far from complete. It omits essential context about deletion scope, safety, and return behavior. The output schema exists but is not referenced, and the agent is left without enough information to use the tool correctly in many scenarios.

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 2 parameters with 0% description coverage. The description only hints at object_ref via 'by entry/name', but with_children is completely unexplained, leaving its meaning and default behavior (true) opaque. This fails to compensate 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 uses a specific verb 'Delete' and resource 'GEOM study object' with reference method 'by entry/name', making the action unambiguous. It clearly distinguishes itself from sibling tools like copy_object or rename_object, and requires no guessing about the 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?

No guidance is provided on when to use this tool vs alternatives or under what conditions deletion is appropriate. The description lacks prerequisites, exclusions, or context about irreversible consequences, leaving the agent to infer usage solely from the tool name and 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?

No annotations are provided, so the description carries the full burden for behavioral disclosure. It indicates duplication (creating new objects) but does not say whether the original is modified, how duplicates are named, or the effect of count values (e.g., zero or negative).

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

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

A single, direct sentence with no filler. The verb is front-loaded, and every word adds value. Ideal conciseness.

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

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

For a simple tool, the description establishes core function, but lacks usage guidance and mentions only two of three parameters. An output schema exists, so return value documentation is not necessary, but with no annotations and 0% schema descriptions, more behavioral and parameter context 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?

The description gives meaning to 'count' (N) and 'source_ref' (source object), but does not mention 'name_prefix' or explain parameter defaults/behavior. With 0% schema description coverage, this partial compensation is helpful but incomplete.

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 states a specific verb ('Create') and resource ('GEOM duplicates') with a clear scope ('from one source object'). The mention of 'N' implies multiple copies, distinguishing it from sibling 'copy_object' which likely creates a single copy.

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 on when to use this tool versus alternatives like 'copy_object' or other transformation tools. The description only describes functionality without indicating preferred use cases or excluding scenarios.

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

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

With no annotations, the description must disclose behavioral traits. It mentions that code is executed and a `result` variable can be returned, but it does not warn about potential side effects, state changes, or the destructive capability of arbitrary code in a SALOME process. This is a significant transparency gap for such a powerful 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 two sentences long, front-loads the core purpose, and contains no unnecessary words. Every sentence adds value, making it highly concise and well-structured.

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

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

Despite having an output schema, the description does not provide essential context for a code execution tool: it omits that the code runs in the SALOME Python interpreter, can mutate the study, and should be used for custom operations. The minimal detail leaves the tool underspecified given its power and 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 schema has one undocumented parameter (code), so the description partially compensates by explaining that the code can set a `result` variable to be returned. This gives the parameter meaning, but it lacks examples, environment details, or error handling expectations, leaving room for improvement.

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 a specific verb and resource: 'Execute arbitrary Python code in the SALOME process.' It distinguishes itself from sibling tools that perform specific operations by emphasizing arbitrary code execution, making the purpose unmistakable.

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

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

There is no explicit guidance on when to use this tool versus its siblings. It does not mention that it serves as a fallback for operations not covered by dedicated tools, nor does it provide any contextual cues for appropriate usage beyond the generic description.

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 of disclosing side effects. It mentions adding subshapes to the study but does not state whether the original object is modified, whether new objects are created permanently, or what happens with different subshape_type values. This leaves significant behavioral ambiguity.

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

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

The description is a single, concise sentence with no filler or redundancy, making it easy to parse. However, it is arguably too terse, omitting necessary details, but this overconciseness is better captured by completeness rather than conciseness.

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 has five parameters, no annotations, and an output schema that is not described in the text. The description leaves numerous questions unanswered, such as naming conventions via result_prefix, allowed subshape types, and the effect of sorted_centres, making it inadequate for the tool's complexity.

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

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

Schema description coverage is 0%, so the description must compensate for the five parameters, but it only hints at 'add them to study' for add_to_study. It does not explain result_prefix, subshape_type (e.g., valid values like FACE, EDGE), or sorted_centres, leaving the agent unable to correctly set these 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 uses the specific verb 'Explode' and identifies the resource as 'GEOM object' and the output as 'subshapes', clearly stating the core function. However, it does not explicitly distinguish this from sibling tools like list_subshapes, which also deal with subshapes, so it is clear but not fully differentiating.

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 explode_shape versus alternatives such as list_subshapes, nor does it mention prerequisites like having a valid GEOM object. The only hint is 'optionally add them to study,' which implies a choice but does not specify appropriate 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 full burden. It only restates the core action without disclosing behavior such as file writing, required file extensions, whether existing files are overwritten, or any side effects.

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

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

The description is a single concise sentence that is easy to parse and front-loaded with the verb. However, it is under-specified to the point of being terse, lacking explanations of parameters or usage.

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

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

For a tool with 5 parameters, 2 required, and no annotations, the description is inadequate. It does not explain how to specify shape_ref or filepath, what format options exist, or any constraints like allowed extensions.

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

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

Schema description coverage is 0%, and the description adds no parameter information. Params like shape_ref, filepath, format, ascii_stl, and stl_deflection remain unexplained, so the agent cannot determine parameter semantics.

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 action 'Export GEOM object' and specifies target formats BREP/STEP/IGES/STL. This distinguishes it from sibling tools like export_mesh (mesh formats) and import_geometry (import direction).

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 on when to use this tool versus alternatives. It does not mention export_mesh for meshes or import_geometry for importing, nor any prerequisites like needing a GEOM object.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It only states the basic action without mentioning file overwriting, required mesh references, or potential side effects.

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

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

The description is a single, front-loaded sentence that immediately communicates the tool's function with no filler. It earns its place by being clear and direct.

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 five parameters and absence of annotations, this one-line description is insufficient. It does not explain parameter roles or behavioral details, and the presence of an output schema does not compensate for the missing context.

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 five parameters, the description provides no explanation of mesh_ref, filepath, ascii_stl, or auto_dimension. The mention of MED/UNV/STL only hints at the format parameter without clarifying its behavior.

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

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

The description 'Export mesh to MED/UNV/STL' clearly states the tool's purpose with a specific verb (export) and resource (mesh) plus target formats. This distinguishes it from siblings like export_geometry or import_mesh.

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 such as export_geometry or create_mesh. The description lacks any context about prerequisites, scenarios, 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 full responsibility for disclosing behavior. It only says 'fuse' and 'convenience wrapper', but does not mention whether objects are modified in place, what side effects occur, if specific permissions are needed, or if a new object is returned. This is insufficient for a mutation tool without annotation support.

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

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

The description is a single sentence with no fluff, front-loading the core action. It is concise and well-structured. However, it is almost too brief, omitting useful context that could be included without affecting conciseness, so it is not a perfect 5.

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

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

The tool has no annotations, a sparse schema with no descriptions, and a one-sentence description. While an output schema exists (so return values may not need explanation), the description lacks critical context about fuse behavior, side effects, or when to choose this over siblings. For a no-annotation tool, this is incomplete.

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 by explaining parameters. It does not explain 'base_object', 'tool_objects', or 'result_name' beyond the generic phrase 'Fuse GEOM objects'. The parameter names are somewhat self-explanatory, but the description adds no additional meaning beyond what the schema properties already provide.

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 fuses GEOM objects, using a specific verb and resource. It also distinguishes itself as a 'convenience wrapper for boolean fuse', which hints at its relationship to the boolean_operation sibling. However, it does not elaborate on what 'fuse' entails geometrically, so it's not a perfect 5.

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

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

The phrase 'convenience wrapper for boolean fuse' implies this tool is for fusing operations, providing context on when to use it. But it does not explicitly state when to use this versus boolean_operation or other boolean tools like cut_objects or common_objects. There are no exclusions or alternative tool mentions, so guidance remains implicit.

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

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

No annotations are provided, so the description must carry the full burden of disclosing behavioral traits. 'Return' implies a read-only operation, but the description does not explicitly state side-effect-free behavior, potential errors, or requirements like an active SALOME session. It also leaves 'detailed SMESH info' vague.

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

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

The description is a single, front-loaded sentence that directly states the tool's purpose. It contains no filler, redundancy, or irrelevant details, making it appropriately concise for a simple retrieval tool.

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

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

The presence of an output schema means the description does not need to explain return values, but the overall context is thin. The tool has one parameter with no explanation, no annotations, and no usage guidance. For a straightforward getter, this is minimally adequate but lacks richness.

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

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

Schema description coverage is 0%, and the description does not explain what 'mesh_ref' refers to. While the parameter name and tool name imply it is a reference to a mesh, the description adds no explicit meaning. Given the low coverage, the description should compensate, and it does not.

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

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

The description uses a specific verb ('Return') and clearly identifies the resource ('mesh counts and detailed SMESH info'). It distinguishes itself from sibling tools like get_object_info by focusing on mesh-specific data. Even without explicit comparison, the tool's purpose is 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?

The description provides no guidance on when to use this tool versus alternatives like get_object_info or list_study_objects. There is no mention of context, prerequisites, or exclusion conditions, so the agent is left to infer usage from the name alone.

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

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

No annotations are present, so the description carries the full burden. It does disclose the return contents (name, bbox, basic properties, subshape counts), which is useful. However, it does not mention the purpose or cost of 'precise_bbox', nor any prerequisites or side effects, which would be valuable 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 a single, focused sentence that front-loads the verb and resource. It lists examples of the returned info without unnecessary words, achieving maximum conciseness.

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?

An output schema exists, so return values need no detailed explanation, and the description gives a good summary. However, it lacks guidance on parameters, and given the many sibling tools, usage context is not fully addressed. The tool is simple, so this is acceptable but not complete.

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

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

The schema has 0% description coverage, and the description does not mention either parameter. 'object_ref' and 'precise_bbox' are somewhat self-explanatory from names, but the description fails to add meaning or clarify their usage or impact, leaving the agent to infer from names alone.

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

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

The description uses a specific verb ('Return') and resource ('GEOM object info') and lists concrete items (name, bbox, basic properties, subshape counts). This clearly distinguishes it from sibling tools like get_mesh_info or list_study_objects.

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 when to use the tool (when you need an object's info), but it does not explicitly state alternatives or exclusions. With siblings like get_mesh_info and list_study_objects, more explicit guidance would be helpful, but the context is still understandable.

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 responsibility for behavioral disclosure. It mentions the 'active study' dependency but does not explain failure modes, whether the operation is read-only, or how limit_per_component affects results. This is insufficient for an unannotated tool.

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

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

The description is a single, focused sentence with no redundant words. It is front-loaded with the verb and resource, making it immediately scannable and appropriately concise.

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?

Although an output schema exists, the description lacks crucial context about what 'scene summary' entails and how the limit parameter behaves. It does not explain when to use this tool or how it integrates with the active study, leaving important gaps for a tool with only one parameter.

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%, and the description does not mention the 'limit_per_component' parameter at all. The agent must rely solely on the parameter name and default value, which is a significant gap since the description adds no 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 a specific action ('Return') and resource ('GEOM and SMESH scene summary for the active study'), making it distinct from sibling tools like get_mesh_info or get_study_info. It immediately conveys both the scope and the module focus.

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

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

There is no guidance about when to use this tool versus alternatives such as get_object_info or get_mesh_info. The description only states what it does, leaving the agent to infer appropriate usage from the tool name.

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

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

With no annotations available, the description carries the full burden of behavioral disclosure. The word 'Return' implies a read-only operation, but the description does not explicitly state that it avoids side effects, nor does it mention any prerequisites such as an active study or possible error conditions.

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

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

The description is a single, front-loaded sentence that immediately states the action and target. There is no wasted information.

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

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

The output schema exists and covers return values, and the tool has no parameters, so the description is nearly sufficient. However, it does not clarify what 'current study' means or whether a study must already be loaded, which is an important prerequisite for a new agent.

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

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

The tool has zero parameters, so the baseline is 4. The description correctly does not attempt to explain parameters because there are none.

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 'Return high-level information about the current SALOME study' clearly states a specific verb+resource and distinguishes from siblings like get_object_info and get_mesh_info. However, 'high-level information' is somewhat vague, leaving the exact scope of returned data unspecified.

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 like list_study_objects or get_scene_summary. There is no mention of prerequisites, exclusions, or context for calling this 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?

With no annotations, the description carries the full burden of behavioral disclosure, but it only states the action. It does not mention side effects (e.g., creating a study object), return behavior, or unit handling, which are critical for an import 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 a single, tightly worded sentence with no filler or redundancy. However, it is arguably too terse for a tool with four parameters, though it remains front-loaded 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?

Despite an output schema existing, the description lacks essential context such as unit auto-handling, format auto-detection behavior, and what happens post-import. For a 4-parameter tool with no annotations, this is incomplete.

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%. The description mentions BREP/STEP/IGES, which offers a vague hint about acceptable filepath values, but it does not explain the 'format' parameter, 'name', or 'ignore_units', leaving most parameters semantically empty.

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

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

The description uses a specific verb ('Import'), identifies the resource ('GEOM'), and specifies source formats ('BREP/STEP/IGES'), clearly distinguishing it from sibling tools like import_mesh or create_* geometry 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 like import_mesh or procedural creation tools. It doesn't mention prerequisites, context, or exclusions, leaving the agent without directional cues.

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 of behavioral disclosure. It only says 'Import mesh' without explaining side effects, such as whether the mesh is added to the study, potential errors, or required environment (e.g., Salome). This is a significant gap for a tool that likely modifies the study 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 a single sentence with no fluff, so it is concise. However, it is under-specified, omitting critical information about parameters and behavior. It is not appropriately sized for the tool's complexity.

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

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

The tool has three parameters, no annotations, and only a minimal description. An output schema exists, but the description does not cover return values or integration context (e.g., where the mesh is imported into). For a tool that imports mesh into a study, the description is too incomplete to guide 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 description coverage is 0%, and the description provides no explanation of the three parameters (filepath, name, format). The format list overlaps with the 'format' parameter but does not clarify its default value ('auto') or how 'name' is used. The description fails to compensate for the lack of schema documentation.

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

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

The description clearly states the tool imports mesh files and lists the supported formats (MED, UNV, STL, CGNS, GMF). This distinguishes it from sibling tools like import_geometry (imports geometry, not mesh) and export_mesh (exports mesh), though it does not explicitly name these 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?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, typical use cases, or exclusions. The format list implies file types, but no explicit context or comparison to sibling tools is given.

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

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

With no annotations provided, the description carries the full burden. It only states the primary action and does not disclose behavioral details like pagination behavior (limit defaults to 200), valid component values beyond examples, or whether a live SALOME session is required. This is a significant gap for a tool that has no safety 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 a single, concise sentence that is front-loaded with the main action and includes the key optional filter. There is no redundant or irrelevant information.

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

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

The description is minimal but adequate for a simple listing operation, given that an output schema exists to describe return values. However, it lacks guidance on usage context, parameter limit semantics, and relationship to sibling tools, making it incomplete for an agent that must select and invoke it correctly.

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

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

The schema has no descriptions (0% coverage), and the description only clarifies the 'component' parameter as an optional filter with examples (GEOM, SMESH). The 'limit' parameter is left completely unexplained, so the description only partially compensates for the schema's lack of information.

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

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

The description clearly states the tool's function with a specific verb and resource: 'List study objects', and adds an optional filter by component, which gives scope. However, it does not explicitly distinguish from related tools like get_study_info or get_scene_summary, so it falls short of 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?

There is no guidance on when to use this tool versus alternatives such as get_object_info or get_study_info. The description only states what it does, not the context or exclusionary cases, leaving the agent without decision support.

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 disclosing behavior. The verb 'List' clearly indicates a read-only, non-destructive operation, but no further context is given about prerequisites, side effects, or ordering. The explicit mention of subshape types adds some detail, but it is basic.

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

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

The description is a single, front-loaded sentence that is concise and free of waste. Every word contributes to the essential meaning.

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 3 parameters, no annotations, and 0% schema description coverage, the description is too sparse. It leaves sorted_centres and return behavior to the output schema. While the output schema may document return values, the overall description does not provide enough context for an agent to use the tool correctly.

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

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

The schema has 3 parameters with zero descriptions (0% coverage). The description partially compensates by enumerating possible subshape types ('FACE/EDGE/VERTEX/SOLID') which relates to subshape_type, and implicitly covers shape_ref via 'for a GEOM object'. However, sorted_centres is completely unexplained, leaving a third of the parameters without semantic context.

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

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

The description states a specific action ('List') and resource ('subshape IDs') with a clear scope ('for a GEOM object'). It differentiates from sibling tools like get_object_info and explode_shape by focusing on enumerating sub-entities rather than retrieving general info or breaking the object.

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 operating on a GEOM object and needing subshape IDs, but provides no explicit when-to-use or when-not-to-use guidance, nor does it name alternatives. The context of operating on geometry objects is clear, but exclusions and alternatives are absent.

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 merely states the action without revealing whether the operation creates a new object, modifies existing ones, requires specific shape types, or has side effects. This is a significant transparency gap for a geometric 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 a single, front-loaded sentence with no fluff, which is structurally concise. However, it is under-specified for a tool with 5 parameters and a nontrivial operation, so the brevity is not entirely appropriate.

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 of a partitioning operation and the lack of annotations, the description is severely incomplete. It does not explain the semantics of partition, the relationship between object_refs and tool_refs, or any behavioral constraints. The output schema may describe return values, but the operational context is missing entirely.

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 compensate. It maps 'objects' to object_refs and 'tools' to tool_refs, but says nothing about shape_type, result_name, or keep_non_limit_shapes. The agent cannot infer parameter meanings beyond their titles.

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 action ('Create') and the resource ('GEOM partition'), and mentions the key inputs ('objects and optional tools'). However, it does not explain what a partition does or how it differs from sibling operations like boolean_operation or fuse_objects, so it could confuse an agent unfamiliar with GEOM.

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 such as cut_objects or common_objects. It lacks context about prerequisites, typical use cases, or limitations, leaving the agent without decision support.

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 states a read-only connectivity check, which implies safety, but does not describe what happens on failure (e.g., error vs. false return) or any other observable behavior. It is minimal but not misleading.

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

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

The description is a single sentence that fully conveys the tool's purpose without any extraneous words. It is perfectly concise and directly 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?

For a simple zero-parameter tool with an output schema present, the description is largely sufficient. However, it does not address likely confusion with the sibling 'check_salome_status', so context completeness is slightly reduced.

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

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

The tool has zero parameters, and the schema is 100% covered trivially. The description does not need to explain any inputs. According to the baseline for 0 params, this scores a 4.

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 action (check connectivity) and the resource (SALOME bridge process). It is specific and unambiguous, but does not explicitly distinguish itself from the sibling tool 'check_salome_status', which might be a similar connectivity/status check.

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 such as 'check_salome_status'. There is no mention of prerequisites, contexts, or comparative rationale, leaving the agent without clear 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It communicates that the operation is a rename and clarifies the reference format, but it does not mention side effects, reversibility, or error behavior, which is a gap for a mutating 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 a single, front-loaded sentence with no redundant words. The parenthetical 'entry ID or existing name' adds precise context without padding.

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

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

For a simple rename tool with an output schema, the description covers the core action and reference format. However, it lacks usage differentiation from sibling tools and behavioral caveats, so it is minimally sufficient but not complete.

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

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

Schema description coverage is 0%, so the description must compensate. It adds that object_ref can be an entry ID or existing name, but it provides no additional meaning for new_name or any constraints on either parameter, leaving the semantic burden largely unmet.

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 'Rename' and the resource 'GEOM study object,' and specifies that the object reference can be an entry ID or existing name. This distinguishes it from related operations like copy or duplicate.

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 explicit guidance is given on when to use this tool versus alternatives such as copy_object or duplicate_object. The verb implies its use, but there are no exclusions or alternative tool mentions, leaving the agent to infer usage.

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 discloses the critical behavioral trait that it modifies the object in place rather than creating a new copy. It also specifies the rotation axis and angle in degrees. However, it does not mention whether the rotation is reversible or whether it rotates about the object origin or global origin.

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

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

The description is a single sentence that gets directly to the point. It front-loads the action and includes only essential qualifiers ('in place', 'no new copy') with no filler.

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

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

The description covers the core mutation behavior but omits important context such as the pivot point for rotation (e.g., object origin vs. global origin) and any preconditions. Since the tool has an output schema, return values are likely covered, but the missing pivot information could affect 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?

The description explains the 'axis' and 'angle_degrees' parameters by mentioning X/Y/Z axis and degrees, respectively. However, the required 'source_ref' parameter is not addressed at all, leaving ambiguity about what it refers to. With 0% schema coverage, the description should compensate more fully.

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 'Rotate', the resource 'GEOM object', and the key distinguishing feature 'in place, no new copy', which differentiates it from copy/duplicate tools. It also specifies the axis and angle units, making the purpose 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?

The description implies its use for rotating existing geometry but does not explicitly state when to choose it over alternatives like translate_object or copy_object. There are no explicit exclusions or alternative recommendations, so it relies on implication.

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 responsibility for behavioral disclosure. It does disclose the key trait of in-place mutation ('no new copy'), which is useful, but it lacks details on coordinate systems, units, error conditions, or whether changes are reversible. This is adequate but not rich.

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

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

The description is a single, front-loaded sentence with no wasted words. It effectively conveys the main purpose and key behavior in a compact form.

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 four required parameters and no annotations, the description is too sparse. It omits critical context such as the coordinate system for the translation vector, the meaning of source_ref, and any preconditions or side effects. While an output schema exists, the description itself does not provide enough context for a new user to invoke the tool correctly without further investigation.

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 meaning by identifying dx, dy, dz as vector components, which is not evident from the bare schema titles (Dx, Dy, Dz). However, it does not explain the units or coordinate system, nor does it clarify that source_ref refers to the object to translate. With 0% schema description coverage, the description provides partial compensation.

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 action (translate), the resource (GEOM object), and the specifics (in place by vector components), distinguishing it from sibling tools like rotate_object and copy_object. The phrase 'in place' explicitly indicates mutation rather than creating a new copy.

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 explicit guidance on when to use this tool versus alternatives is provided. The description implies it is for translating objects, but does not mention exclusions (e.g., not for copying) or alternative tools for other transformations.

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