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

With no annotations, the description carries the full behavioral burden and does well: it discloses that operating on a shared-definition instance consumes only that instance, that the result is a new group leaving siblings untouched, and the non-manifold reliability caveat. It stops short of covering permissions or how delete_originals interacts with shared-definition instances.

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

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

Front-loads the core purpose and then layers in semantics, edge-case behavior, and return interpretation in short sentences. The line breaks are slightly awkward but each sentence carries distinct, useful information 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?

For a mutation tool with no annotations, it addresses result semantics, edge-case reliability, and a subtle scoping behavior, and even interprets the bbox_mm null return despite an output schema existing. The main remaining gap is explicit routing against sibling modeling tools.

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 100%, so the parameters are already documented, and the description largely restates the schema's 'difference (target minus tool)' note. It adds the shared-instance/consumption nuance that bears on how target_id/tool_id behave, but no other syntax or format detail 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?

States a specific verb (perform) and resource (boolean operation on two solids) and enumerates the three operation modes. An agent can immediately distinguish it from the modeling siblings (fillet_edge, chamfer_edge, create_*), which do not overlap this function.

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

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

The description clarifies what each operation means and warns that the tool is unreliable on non-manifold geometry, which is useful selection context. However, it never states when to choose boolean_operation over alternatives or any prerequisites (e.g. solids must overlap), so usage is only implied.

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 behavioral burden and does well: it discloses the default scope (all edges), a reliability limitation (non-manifold geometry), and explains the failure-signalling stats so the agent knows how to verify success. It omits permissions/auth and reversibility (e.g., undo availability), keeping it short of a 5.

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

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

Front-loaded with the core operation, then scope, caveat, and return handling in order. The return-value block is somewhat verbose for a schema that already defines the output, but every clause (the two stats checks) carries actionable 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?

For a destructive edge operation with an output schema present, the description covers scope, a reliability caveat, and how to interpret failure stats. Missing only auth/permission and reversibility notes, which is a modest gap rather than a crippling one.

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

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

Schema coverage is 100%, so id and distance are already documented in the schema (including the mm unit and positivity). The description only restates the distance unit and default-all-edges behavior, adding little beyond the structured fields; baseline 3 is appropriate.

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

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

States a specific verb (chamfer/bevel) applied to a specific resource (edges of a group/component) and quantifies the operation via distance in mm. It is clear what the tool does, though it never names fillet_edge, its obvious sibling, to distinguish bevel from round.

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

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

Implies usage through 'By default ALL edges are chamfered' and a non-manifold reliability caveat, but gives no explicit when-to-use versus fillet_edge or other modeling tools, and no stated prerequisites (e.g., an entity must be selected or referenced by id).

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

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

With no annotations, the description carries the full burden. It usefully discloses units (mm) and the exact JSON return shape including bbox, but is silent on side effects such as whether a named group is created, whether the operation is undoable, or any permission/state requirements.

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

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

Well front-loaded: purpose first, then unit convention, then per-parameter notes, then return shape. Slight redundancy in restating parameter names already titled in the schema, but little waste overall.

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 spelling out the return type is bonus rather than necessary. For a geometry-mutating tool with no annotations, the description leaves side effects (grouping, undo, model state) and the create_circle vs create_curve distinction unaddressed.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds genuine meaning by explaining that normal defines the perpendicular plane and that higher segments yield a more accurate approximation, clarifying the effect of parameters beyond their bare schema text.

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 gives a specific verb+resource ('Create a true circular curve in SketchUp') and pins down scope with units and return shape. It does not, however, differentiate itself from the sibling create_curve, which an agent would plausibly reach for instead.

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 when-to-use guidance, no prerequisites, and no mention of alternatives such as create_curve or create_component. The agent must infer when a circle is appropriate versus a generic curve.

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

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

No annotations provided, so the description fully covers behavioral traits: units (mm), minimum dimensions per type, position as MIN corner, per-type dimension conventions, return value details, and suggestion to verify with bbox_mm. Thorough disclosure.

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

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

Multiple sentences but each adds essential detail without redundancy. Well-structured: purpose, units, size constraints, anchor point, per-type dimension mapping, Group wrapping, return value and verification advice. Efficient and front-loaded.

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

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

Given 100% schema coverage and presence of output schema, the description provides all necessary context: explains param nuances (ignored axis for cylinder/cone), behavioral constraints, and return format. No gaps for a primitive creation tool.

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

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

Schema description coverage is 100% (baseline 3), but description adds significant value: minimum sizes (0.1mm cube, 1.0mm sphere/cylinder/cone), clarifies that dimensions are interpreted differently per type (e.g., cylinder [0]=diameter, [2]=height), and reinforces that position is MIN corner.

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

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

Clearly states it creates a primitive (cube/cylinder/cone/sphere) in SketchUp and that geometry is wrapped in a Group. Distinguishes from transform_component by noting shared anchor convention, and from sibling creation tools by specifying primitive types.

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

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

Provides clear instructions on when to use (to create primitives) but does not explicitly state when not to use or compare to alternative creation tools like create_dovetail or create_finger_joint. However, it references transform_component for positioning, offering some guidance.

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

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

With no annotations, the description carries full burden, and it does add real behavioral context: coordinates are in mm, points are model coordinates, the result is wrapped in a SketchUp Group, and closed=true connects endpoints. However it omits error handling, whether the model must be open/active, and undo implications of a geometry-mutating call.

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

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

Front-loaded with the core action, then short scoped notes. Efficient and readable, though the return-value block is somewhat redundant given an output schema exists.

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

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

Covers coordinates, grouping, closed semantics, and return shape, which is sufficient for an agent to invoke it. For a mutation tool with no annotations, it could say more about side effects or preconditions, keeping it from a 5.

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 100%, so the baseline is 3. The description reinforces the mm/coordinate interpretation of points and elaborates on closed, but adds little meaning beyond what the schema already documents.

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?

States a specific verb and resource: 'Create a SketchUp curve from 3D points,' which is unambiguous. It does not name any sibling (e.g. create_circle) to differentiate, so it stops short of a 5.

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

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

No guidance on when to use this versus siblings like create_circle or create_component, and no prerequisites (e.g. an open model). Usage is only implied by the purpose statement.

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 and does well: it declares units (mm, degrees), the valid angle range, that offsets are relative to the board face center, that defaults assume ~100 mm boards, and that the operation is a mutable geometry creation. It stops short of stating reversibility/undo behavior or what happens to pre-existing geometry.

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

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

Three short blocks — action, dimensional conventions, return shape — each front-loaded and free of filler. Nothing repeats the parameter schema verbatim, and the constraint that matters most (boards must overlap) is stated plainly.

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 re-describing the return payload is technically redundant, but the added failure semantics (non-zero 'failed' means non-manifold cuts, verify via bbox_mm) is valuable operational context. With preconditions, units, and failure modes covered, only mutation/undo behavior is unaddressed.

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 already 100%, so baseline is 3. The description adds real meaning on top: it unifies the unit convention across all numeric parameters and clarifies that offset_* are measured from the board face center and that defaults are tuned for ~100 mm stock, context the schema does not 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?

States a specific verb and resource ('Create a dovetail joint between two boards'), which is enough to distinguish it from the sibling joint tools create_finger_joint and create_mortise_tenon by joint type. It does not, however, explicitly name or contrast those alternatives, leaving the differentiation implicit in the nouns.

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 precondition 'The two boards must already touch/overlap along the joint axis' is a genuinely useful usage constraint. Beyond that, there is no guidance on when to choose a dovetail over a finger joint or mortise-tenon, so the when-to-use dimension is only implied.

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, and it does well: it states units, that defaults are tuned for ~100 mm boards, and critically discloses failure behavior (non-zero 'failed' means cuts didn't apply, likely non-manifold geometry) plus a verification path via bbox_mm. It omits mutation side-effects such as whether the boards are modified in place or reversibility.

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

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

Front-loads the purpose, then constraints, then return shape in three compact blocks with no filler. Slightly dense in the returns sentence, but every clause carries information.

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

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

For a 9-parameter geometry mutation with no annotations, the description covers units, preconditions, default sizing, and failure interpretation. An output schema exists so return details were not strictly required, yet the explicit failure guidance is a genuine addition; only mutation side-effects remain unstated.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema lacks: offsets are measured from the board face's center, all values are in mm, and the default set is sized for ~100 mm boards. That is real interpretive value beyond the per-field schema text.

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?

States a specific verb and resource ('Create a finger joint (box joint) between two boards') and even supplies the synonym 'box joint'. It does not explicitly contrast itself with siblings like create_mortise_tenon or create_dovetail, but the joint type is definitionally distinct so an agent can still select it.

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

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

Provides a concrete applicability precondition: 'The two boards must already touch/overlap along the joint axis.' That tells the agent when the call is valid. It does not, however, name alternatives (mortise-tenon, dovetail) or state when-not-to-use, so it falls short of a 5.

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

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

No annotations are provided, so the description must disclose behavioral traits. It states the tool creates a layer and returns {id, name, visible}, which covers mutability and output. However, it does not disclose any side effects, permissions, rate limits, or constraints beyond the schema (minLength). For a simple creation tool, this is adequate but minimal.

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—two sentences: one for purpose and one for return value. No unnecessary words, front-loaded with the action. Every sentence adds value.

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

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

Given the tool's single parameter and the presence of an output schema (which the description explicitly echoes), the description is complete. It covers purpose, input, and output. No critical information is missing for an agent to use this tool correctly.

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

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

Schema coverage is 100% for the single parameter 'name', which already has a description. The tool description adds no additional meaning beyond the schema for this parameter (just 'with the given name'). Baseline 3 is appropriate.

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

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

The description clearly states the verb 'Create' and the resource 'new layer (tag)' with a required name parameter. It distinguishes from sibling list_layers which reads layers, and other tools that modify components. The return format is also specified.

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

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

The description implies usage for creating a layer, but does not explicitly state when to use this tool versus alternatives like list_layers or other creation tools. No when-not or exclusion criteria are provided, but the simplicity of the operation mitigates the need for extensive guidance.

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

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

With no annotations provided, the description carries the full burden and does well: it discloses the failure mode (non-zero 'failed' means cuts did not apply, likely non-manifold geometry), tells the agent how to verify (bbox_mm), and states the geometric precondition. It does not mention permissions, reversibility, or whether the operation is destructive/undoable.

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

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

Front-loaded with the action, then units/scaling, then the precondition, then a labeled 'Returns' block. No filler sentences; each line (units, offsets, defaults, precondition, return contract) earns its place.

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

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

For an 8-parameter geometry mutation with no annotations, the description covers units, offset semantics, default scaling, a precondition, and failure interpretation. An output schema exists, so the added 'Returns' detail is a bonus rather than a necessity, and the only real gap is the absence of any undo/reversibility or permission note.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: all dimensions are in millimeters, offsets shift relative to the board face's center, and the defaults are calibrated for ~100 mm boards. That contextual sizing information is not derivable 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?

States a specific verb and resource ('Create a mortise-and-tenon joint between two boards') and implicitly distinguishes itself from sibling joint creators (create_finger_joint, create_dovetail) by naming the joint type. An agent can tell which joint operation to call without opening any schema.

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

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

Provides a real precondition ('The two boards must already touch/overlap along the joint axis'), which is useful usage context. However, it gives no guidance on when to choose this over the other joint-creating siblings or what to do when the precondition fails. Adequate but with a clear gap.

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

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

No annotations are provided, so the description must disclose behavioral traits. It states the return value but fails to warn about permanent data loss or side effects. For a delete operation, this is insufficient.

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

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

The description is extremely concise with two sentences, no redundant information, and the key information is 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?

While the tool is simple with one parameter and an output schema, the description lacks details on error handling, idempotency, and permission requirements, which are important for a delete operation.

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

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

The schema already fully describes the 'id' parameter (100% coverage). The description only repeats 'by entity ID', adding no additional semantic value beyond what the schema provides.

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

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

The description clearly states the action ('delete') and the resource ('group or component') and specifies the method ('by entity ID'). It distinguishes itself from sibling tools, as it is the only deletion operation among 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?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or conditions for safe use. Given the destructive nature, such guidance is important.

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 behavioral burden and does so well: it discloses the settings gate, the exact JSON-RPC error code (-32010), that stdout is not captured, that only the last expression's .to_s returns, and the error format. These are exactly the traits an agent needs. It stops short of 5 only because it doesn't state permission/security implications beyond the gate.

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

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

Front-loaded with the core purpose, then organized into gate behavior, return semantics, and error format. Each sentence earns its place and there is minimal redundancy. Slightly dense but appropriate for a tool with subtle execution semantics.

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 an output schema exists, the description needn't enumerate return fields, and it still explains the critical return mechanics (last expression, no stdout). With no annotations, it fully compensates by covering the settings gate, error codes, and error string format. Nothing an agent needs to invoke this correctly appears missing.

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

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

Schema coverage is 100% and there is a single required 'code' parameter well documented in the schema. The description adds real semantic value beyond the schema by explaining what the code should return (last expression's .to_s, not stdout) and the recommended output convention. Baseline for a 1-param tool with full coverage would be 3-4; the return-semantics guidance justifies the 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?

States a specific verb+resource: evaluate arbitrary Ruby code in SketchUp. This is clear and distinguishable from the sibling modeling tools (chamfer_edge, create_component, etc.), which perform CAD operations rather than code execution. It lacks an explicit 'use this for X, not Y' routing statement, keeping it from a 5.

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

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

The description implies usage through the return-value mechanics (e.g., end with result.to_json), which hints at when this tool is useful for structured data. However, it never states when to choose this tool over siblings, nor any explicit conditions of use. Usage is inferable but not spelled out.

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 and does so well: it discloses that the file lands on the SketchUp host, that the path is unreadable on a split-host setup, and that skp export from a never-saved model emits a warning tied to SketchUp binding the live document to the export path. It omits overwrite behavior and any permission requirements, keeping it short of a 5.

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

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

Front-loaded with the core action, then cleanly segmented into "Formats:" and "Returns:" blocks; nothing is padding. The formats line duplicates the enum description in the schema nearly verbatim, which is a minor redundancy.

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

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

For a single-parameter tool with an output schema, the description supplies everything the schema cannot: host-side file location, the split-host readability caveat, and the meaning of the conditional "warning" field. An agent has all it needs to call this correctly and relay results.

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

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

Schema coverage is 100% with an enum, so the baseline is 3, but the description adds information the schema lacks — the default 1920×1080 viewport resolution for png/jpg. The format grouping itself largely restates the schema's own enum description.

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?

States a specific verb and resource ("Export the current scene to a temp file") and enumerates supported output formats, so the agent knows exactly what is produced. It does not, however, differentiate itself from the closest sibling get_viewport_screenshot, which also yields image output via the png/jpg formats.

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 format list and the temp-file destination, giving the agent a reasonable sense of when a file export is appropriate. There is no explicit when-not guidance, no prerequisites, and no pointer to alternatives such as get_viewport_screenshot for viewport captures.

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 discloses the destructive/mutating nature (edges are consumed by cuts), the reliability caveat on non-manifold geometry, and the return stats with explicit success criteria. It does not mention permissions or reversibility, but the failure-mode disclosure is strong.

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?

Four compact sentences: operation, default scope, caveat, return contract. Front-loaded with the core action and every sentence carries information. The escaped quotes are a minor formatting artifact but do not obscure 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?

An output schema exists, yet the description still summarizes the returned JSON and states how to interpret stats (subtract_failed == 0, skipped_no_match == 0), which is high-value guidance for an agent deciding success. Combined with the mutation caveat, this is complete enough to invoke correctly.

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

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

Schema description coverage is 100%, so the schema documents all three parameters, including defaults and units. The description reinforces radius and segments but adds no syntax or format details beyond the schema. Baseline 3 applies.

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?

States a specific verb (Round/fillet) and resource (edges of a group/component) with the key parameters named. The sibling chamfer_edge is a distinct operation, and the description makes the operation 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?

States a default behavior ("By default ALL edges are filleted") and a caveat ("Unreliable on non-manifold geometry"), which gives implied context. However, it does not specify when to use fillet_edge vs chamfer_edge or how to limit the edge selection, leaving the agent to infer.

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 and largely meets it: it discloses case-insensitive substring vs exact layer matching, recursive traversal bounded by max_depth, pagination via offset/limit, and truncation handling ('offset += limit'). It does not state permission requirements or whether the traversal is expensive on large scenes, leaving minor gaps for a read tool with no 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?

Three tight paragraphs, front-loaded with the core operation, then filter semantics, then pagination/return behavior. Every sentence carries information an agent needs; nothing is repeated 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 7-parameter, all-optional search tool, the description covers operation, filter semantics, traversal bounds, and pagination. An output schema exists so return values needn't be explained, yet the description still clarifies the truncation/next-page workflow, leaving no practical gap.

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

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

Schema coverage is 100%, so the 3 baseline applies, and the description goes beyond it by explaining how filters combine ('and/or'), that layer matching is exact while name matching is substring, and how offset/limit interact with the truncated flag. It adds real semantics on top of the already-documented 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?

States a specific verb and resource ('Find components') plus the exact filterable dimensions (name substring, layer, type), which is enough for an agent to understand the operation without opening the schema. It also explicitly contrasts its no-filter behavior with the sibling list_components ('same traversal as'), separating it from the nearest alternative.

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

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

The description gives clear usage context: with filters it narrows results, with no filters it behaves like list_components up to max_depth. That implicitly routes the agent away from this tool when no filtering is needed, but it never explicitly states when to prefer get_component_info, get_selection, or list_components, so guidance is clear but not exclusionary.

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 states the return format but does not disclose error behavior, permissions, or that it is read-only. For a simple getter, this is minimally acceptable.

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

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

Two sentences fix, no unnecessary information. Concisely states purpose and return format.

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 simple input and presence of output schema, the description is largely complete. It could mention error handling or that the ID must come from previous responses, but overall is sufficient.

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 100%, so baseline is 3. The description does not add new meaning beyond the schema's parameter description.

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

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

The description clearly states the tool retrieves detailed info for a single group or component by entity ID, distinguishing it from sibling tools like find_components, list_components, and get_selection.

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 the user has an entity ID, but lacks explicit guidance on when to use versus alternatives, or when not to use 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 carries the burden. It implies a read-only operation but does not explicitly state that it does not modify the model or any side-effect guarantees.

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

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

Two sentences, no waste. The first sentence states purpose, the second lists return format concisely.

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 info retrieval tool with no parameters and an output schema, the description is largely sufficient. However, it misses potential preconditions (e.g., model must be open) and failure modes.

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?

No parameters exist (0 params), baseline is 4. The description adds value by detailing the return structure beyond the empty schema.

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

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

The description clearly states 'Get current SketchUp model info' and lists all returned fields (path, title, units, etc.). It is specific and distinct from sibling tools like get_component_info which focus on individual components.

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 vs alternatives. The context is implied as a general model information retrieval, but there is no mention of when not to use it 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 carries the behavioral burden. It conveys that this reads the live UI selection state (not a stored list) and that the result varies with what the user has picked, which is useful context. It does not, however, state that it is read-only/no-side-effect, what happens with an empty selection, or any limits, so it only partially compensates for the missing 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?

Front-loads the purpose in one sentence, then details the return shape compactly. Efficient with no filler, though the return-shape sentence partly duplicates the output schema and thus is not strictly necessary.

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

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

For a zero-parameter read tool with an output schema already present, the description is essentially complete: purpose, scope, and a breakdown of the returned entity shapes. Minor gaps remain around empty-selection behavior and read-only guarantees, but nothing essential to calling it correctly is missing.

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 takes zero parameters, so there are no parameter semantics to explain and the baseline of 4 applies. The schema description coverage is 100% and nothing about arguments needs further clarification.

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?

States a specific verb ('Get') and resource ('entities currently selected in the SketchUp UI'), with the scope qualifier 'currently selected' distinguishing it from sibling readers like get_model_info, list_components, or find_components. An agent can identify this as the live-selection reader without opening any schema.

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 name and description (call it to read what the user has selected), but there is no explicit when-to-use guidance, no exclusions, and no comparison to alternatives like get_model_info or list_components that also enumerate entities. Adequate but leaves the routing decision to inference.

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 behavioral burden and does reasonably well: it discloses the notable guarantee that a payload is always returned even on connection failure, and that errors surface in an 'error' field rather than as a thrown failure. It omits side-effect/auth context, but for a pure version probe that is a minor 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 purpose and the probe rationale are front-loaded in the first two sentences, which is good structure. The final enumeration of return fields is partly redundant against the existing output schema, costing a little 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 the description need not explain return values — and its field list is therefore surplus rather than a gap. What an agent needs (what it returns, and that it always succeeds) is present, though no auth or rate-limit context is given.

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?

There are zero parameters, so the baseline is 4. The description correctly implies no inputs are needed and adds nothing misleading about 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?

States a specific verb and resource ('Return the server version and Python↔Ruby compatibility verdict') and names the exact verdict it produces, which no sibling tool does. An agent can distinguish it from get_model_info, get_component_info, and get_selection purely from the description.

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?

Gives a clear usage context — 'useful as a runtime sanity probe' — and explains why it is preferable when other calls fail. It does not name an alternative tool or state when not to use it, but the context is explicit enough to route the call correctly.

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 describes the snapshot process, parameter effects, and retry/flicker behavior. It does not explicitly state non-destructiveness but implies it via the restore_view parameter and its description.

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

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

The description is well-structured with clear paragraphs and a parameter list. It is concise enough but could be slightly tighter by removing some redundancy.

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

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

Given no output schema, the description includes the return format (PNG + JSON). It covers all parameters, retry behavior, and the purpose, making it fully informative 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 coverage is 100%, but the description adds significant context beyond the schema for each parameter, such as aspect ratio scaling for max_size and the specific rendering options toggled by style.

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 captures a screenshot of the SketchUp viewport and returns a PNG image along with a JSON block containing dimensions and style info. It is distinct from sibling tools like export_scene or get_selection.

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

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

Explicitly states it is 'useful for letting Claude visually verify the scene between steps', providing clear context for when to use it. However, it does not explicitly mention when not to use it or compare with alternatives.

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

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

With no annotations present, the description carries the full behavioral burden and does so fairly well: it discloses the return shape, the truncation flag, the pagination recovery step (offset += limit), depth bounding, and that bboxes are world-coordinate millimeters. It stops short of stating read-only/safety characteristics or any rate limits, so it is strong but not complete.

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

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

Front-loaded with the core purpose, then return shape, then pagination recovery — a logical order. The brace-notation field lists are dense but information-carrying, and nothing is redundant; it is slightly long for the task but every clause earns its place.

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

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

For a paginated read tool with five documented parameters, an output schema, and no annotations, the description supplies everything an agent needs: scope, pagination contract, depth semantics, response variants, and coordinate units. Nothing material is missing.

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

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

Schema coverage is 100%, so the schema already defines all five parameters and the baseline would be 3. The description still adds genuine meaning on top: the concrete effect of response_format on bbox_mm, the default max_depth of 3 and its interaction with recursive, and the pagination arithmetic using offset and limit.

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?

States a specific verb and resource: list groups and component instances in the model, with pagination noted. It is clear what the tool returns, but it never names or contrasts with siblings like find_components or get_component_info, leaving the agent to infer that filtering belongs elsewhere.

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 only implied through parameter hints ('Set recursive=true to descend into nested components'), which is really parameter guidance rather than when-to-use guidance. There is no statement of when to prefer this over find_components for searching, or when get_component_info is the better call for a single item.

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

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

No annotations provided, so description carries full burden. It mentions return format and that it lists all layers, implying a read-only operation but does not explicitly state no side effects. Adequate for a simple 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?

Very concise, single sentence plus return format example. Structurally clear and front-loaded.

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

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

Given zero parameters and presence of output schema in description, it is fairly complete. Lacks details on layer definitions or edge cases, but sufficient for a simple list tool.

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

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

No parameters exist, so schema coverage is 100%. Baseline of 3 applies; description adds no parameter information, which is acceptable given no params.

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 lists all model layers (tags). The verb 'list' and resource 'layers' are specific. The parenthetical 'tags' might cause minor ambiguity but overall the purpose is clear.

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

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

No explicit guidance on when to use this tool versus alternatives (e.g., create_layer). However, as a simple read operation with no parameters, usage context is implicitly understood.

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 behavioral burden and does so thoroughly: it lists accepted material formats, case-insensitivity, error code -32602 for invalid input, the side effect of making an instance unique before painting, and the distinction that painting raw face/edge ids affects shared definitions. It also describes the return shape, though an output schema exists.

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

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

The description is front-loaded with the core purpose, followed by important behavioral details in a logical order. Sentences are information-dense and mostly earn their place, though the final 'Returns' line is slightly redundant given the output schema. Overall, it is efficient and well-structured.

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

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

For a two-parameter mutation tool with no annotations and an existing output schema, the description provides a complete picture: accepted inputs, error handling, side effects, special-case behavior for raw ids, and return shape. Nothing critical for correct invocation is missing.

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

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

Schema coverage is 100%, so the schema already documents both parameters. The description exceeds the baseline by enumerating all accepted named colors, specifying the hex format (#rrggbb), noting case-insensitivity, and explaining the error behavior for invalid materials. It adds meaningful context beyond the schema's brief parameter descriptions.

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

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

The first sentence states a specific verb (Assign) and resource (material/color) to a group or component. It immediately distinguishes the tool's function from all siblings, none of which set materials. The description leaves no ambiguity about what the tool does.

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 clear purpose statement, and the description provides context about different behaviors for groups/components versus raw face/edge ids. However, it does not explicitly state when to use this tool versus alternatives, nor does it list any prerequisites or exclusions. The guidance is present but not direct.

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 and does so: it discloses application order (position applied LAST, after rotation/scale), idempotency ('repeating the same position is idempotent', 'NOT a relative offset'), sequential axis order for rotation, the validation behavior and its bypass via eval_ruby, and the shape of the return including that bbox_mm is null for empty geometry.

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

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

Front-loaded verb+resource line, then bulleted per-parameter semantics, then validations and return shape — a clean, scannable structure where each block carries weight. There is some overlap with the schema descriptions (position/rotation/scale phrasings are echoed), which slightly dilutes 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 4-parameter mutation tool with no annotations, the description covers sequencing, idempotency, validation rules, the eval_ruby escape hatch, and the return payload including the null-bbox edge case. An agent has everything needed to 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantics beyond the schema text: that position targets the bbox MIN corner specifically, that it is applied after rotation/scale so combined calls land exactly at [x,y,z], and that repeating it is idempotent. It does not add further detail on scale bounds beyond what the schema already states.

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?

Opens with a specific verb set and resource ('Move, rotate and/or scale a group or component') and immediately scopes units (mm / degrees). It also names the related sibling create_component as sharing the same anchor, so an agent can place it relative to that tool.

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?

Gives strong context for when this tool is appropriate versus raw Ruby: the validations 'apply only to this typed tool — raw Ruby driven through eval_ruby bypasses them', implying use this when validation matters. However, it never states an explicit when-not rule or a preferred alternative in the way a 5 requires.

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

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

With no annotations, the description carries the full burden. It discloses that it undoes the last atomic operation and returns {ok: true}. This sufficiently describes behavior for a straightforward undo 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 consists of two short sentences: one explaining the action and one specifying the return value. Every word adds value with no redundancy.

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

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

Given no parameters and a simple return, the description is complete. It omits potential edge cases (e.g., multiple undos), but overall it provides sufficient context for a basic undo tool.

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

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

There are no parameters (0 parameters, 100% schema coverage). The description adds no extra parameter info, which is fine as the schema already covers everything.

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 'Undo the last atomic operation in SketchUp', using a specific verb and resource. It is distinct from sibling tools which create, modify, or query; no other tool performs undo.

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 explains that one MCP tool-call equals one undo step, clarifying usage. No explicit when-not-to-use or alternatives are given, but the simple 0-parameter interface and unique function make guidance adequate.

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