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

With no annotations, the description carries the full burden. It discloses key behavior (rotation inside node) but omits side effects (e.g., overwriting existing transforms, auth requirements, or constraints on parameter combinations).

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 efficiently communicates the core functionality with no redundant words.

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

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

Given the tool has 6 parameters and no output schema, the description is too minimal. It lacks explanation of parameter interactions, default behaviors, or expected results, leaving the agent underinformed.

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 description adds no additional meaning beyond the schema for parameters. The tool's one-sentence description does not elaborate on parameter usage or constraints.

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 adjusts image position, scale, and rotation within a node, and explicitly distinguishes rotation from node rotation, making it distinguishable from sibling tools like rotate_node.

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 scenarios (adjusting image transform) but provides no explicit guidance on when to use this over alternatives like set_image or rotate_node, nor any prerequisites or limitations.

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

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

No annotations are provided, so the description bears full responsibility. It states the binding action but does not disclose side effects (e.g., overwriting, reversibility), prerequisites (variable must exist), or error scenarios, leaving significant behavioral 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 extremely concise: two short sentences. The first sentence states the purpose, and the second provides a key usage guideline. No unnecessary words, front-loaded, and easy to parse.

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

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

While the description covers the core action and usage pattern, it lacks details about error handling, prerequisites (e.g., variable existence), return values (no output schema), and potential side effects, which would be expected for a mutation tool with no annotations.

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

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

Schema descriptions cover all three parameters, but the description adds value by explaining the 'field' parameter with examples and the per-field calling pattern, which clarifies the intended usage beyond the schema.

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

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

The description clearly states the tool's purpose: binding a variable to a node property in Figma. It distinguishes itself from sibling tools like 'set_variable' by emphasizing the binding action and the per-field usage pattern.

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

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

The description provides a usage guideline: 'Call once per field — for multiple fields, call multiple times.' This indicates when to use and how to batch calls, though it does not explicitly contrast with sibling tools like 'set_variable'.

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

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

No annotations exist, so the description must disclose side effects. It does not state whether the original nodes are deleted or replaced, whether the operation is destructive, or describe the result node. The mention of 'order matters for SUBTRACT' is helpful but insufficient 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?

Single sentence, no wasted words, front-loaded with purpose. Achieves maximum clarity with minimum text.

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 that modifies geometry, the description lacks essential context: what happens to the input nodes, what the result is, and any reversibility. Given the lack of output schema, the description should provide this 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?

Schema description coverage is 100%, so baseline is 3. The description adds the parent constraint, which complements the schema but does not significantly enhance understanding beyond what the schema already 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 explicitly states 'Perform a boolean operation (union, subtract, intersect, exclude) on two or more nodes', using specific verbs and resource (nodes). It differentiates from siblings like group_nodes by specifying boolean operations rather than grouping, and includes a constraint (same parent).

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 vs alternatives (e.g., group_nodes, flatten_node). It does not provide context for when boolean operations are appropriate or when to expect different behavior. The constraint 'All nodes must share the same parent' is a prerequisite but not a usage guideline.

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?

Without annotations, the description carries full burden but only states 'Clone an existing node', omitting behaviors like positioning (via x,y,parentId parameters), return value, or side effects (e.g., new node ID).

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 filler, efficiently conveying the core action.

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

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

Given no output schema and no annotation, the description should mention return values (e.g., cloned node ID) or success conditions, but it does not. The tool's result is unclear for agent planning.

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 parameter descriptions, so the description adds no extra meaning. Baseline 3 is appropriate as it does not degrade clarity.

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 'Clone an existing node in Figma' uses a specific verb ('Clone') and resource ('existing node'), clearly distinguishing it from sibling tools that create new nodes or modify existing ones.

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 other creation or duplication tools. There is no mention of prerequisites (e.g., node must exist) or alternatives.

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

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

With no annotations provided, the description discloses key behaviors: it preserves position, size, visual properties, and children. It also implicitates that the resulting frame supports auto-layout. Missing are details on whether the operation is reversible, if it requires specific permissions, or what happens if the node is already a frame. Overall, transparency is good but not exhaustive.

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 three short, front-loaded sentences. The first sentence states the primary action, the second lists preserved properties, and the third provides a use case. Every sentence adds distinct value, and there is no redundancy or unnecessary detail.

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 one parameter and no output schema, the description covers the core behavior, preservation details, and a use case. It lacks edge case handling (e.g., if node is already a frame) and does not specify the return value or whether the original node ID remains valid. Slight gaps, but sufficient for a simple conversion tool.

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

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

The parameter 'nodeId' has a schema description that is generic ('The ID of the node to convert to a frame'). The tool description adds context by specifying that the node must be a group or shape, which is meaningful beyond the schema. With 100% schema coverage, the description adds value by narrowing the valid node 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 clearly states the action ('convert'), the target resource ('group or shape node into a frame'), and provides specific details about what is preserved (position, size, visual properties, children). It effectively distinguishes from sibling tools like 'group_nodes' or 'ungroup_nodes' by specifying the conversion outcome.

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 mentions a use case ('useful for converting groups into auto-layout-capable frames') but does not explicitly state when not to use the tool or mention alternatives such as 'create_frame' or 'set_auto_layout'. The context is clear but lacks exclusions or comparative 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?

No annotations provided, so the description carries full burden. It only states the basic action ('convert...into a reusable component') without disclosing whether the original node is replaced or kept, side effects, authentication needs, or 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?

Single sentence, front-loaded with verb and noun ('Convert an existing node...'), no wasted words. Efficient and clear.

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

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

The tool is relatively simple, but with no output schema or behavioral disclosure, the description omits return value, constraints (e.g., what node types can be converted), and error handling. Adequate for minimal understanding but not fully complete.

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

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

Input schema has 100% parameter description coverage, so the schema already explains all parameters. The description adds no additional meaning beyond what the schema provides (e.g., name is optional, parentId is required). 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 tool converts an existing node (like frame, group) into a reusable component. It specifies the action and resource, distinguishing it from siblings like 'create_component_instance' which creates instances rather than converting.

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 (e.g., create_component_set). The description does not mention prerequisites, contexts where conversion is not possible (e.g., unsupported node types), or any 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 full burden but only states 'Create an instance', missing details on side effects, required permissions, or mutation behavior beyond the obvious.

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, but it is so brief that it sacrifices informative value; still, no unnecessary words.

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?

Missing annotations and lack of usage context; the description does not inform about return values or behaviors beyond the schema, leaving the agent underinformed for a creation tool with 4 parameters.

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 no extra meaning beyond the schema's 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 description clearly states the verb 'Create' and the resource 'an instance of a component in Figma', making it distinct from siblings like 'create_component_from_node' and 'detach_instance'.

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; fails to mention prerequisites like obtaining a component key via 'get_local_components', and does not provide when-not 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 full burden of behavioral disclosure but only states the creation action. It omits details like side effects on original nodes, required permissions, limitations on node count, or return values, making it minimally informative for an agent.

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 conveys the essential action without redundant words. It is front-loaded and efficiently captures 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?

Given 100% schema coverage and a clear purpose, the description is mostly complete for a creation tool. However, the absence of return value or error info and no behavioral details from annotations slightly reduce completeness, though it remains adequate.

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

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

Schema coverage is 100%, so parameters are well-documented in the schema. The tool description adds no additional parameter meaning beyond the schema, except as implied by the phrase 'from multiple component nodes'. Baseline score 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?

The description clearly states the verb 'Create' and the resource 'component set (variants)' with the source 'from multiple component nodes'. It uniquely identifies the action among siblings like create_component_from_node (single component) and create_component_instance (instance).

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

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

The description provides clear context: use when combining multiple component nodes into a component set. It does not include explicit exclusions or alternative tool names, but the context is sufficient for an agent to infer the appropriate scenario.

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. Mentions parentId is REQUIRED (server enforces) and how to get page IDs. However, lacks disclosure of side effects, auth requirements, rate limits, or what happens if parameters conflict. Limited transparency.

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, front-loaded purpose, then brief parameter hint. No redundant information. Efficient and clear.

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

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

Core purpose and two usage modes explained. Notes parentId requirement but lacks examples, format details for strokeColor, or clarification on mutual exclusivity of parameters. Adequate but not exhaustive for a 13-param 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 coverage is 100%, baseline 3. Description adds value by explaining two modes (node ID vs coordinates) and implicitly mapping parameters. Also notes default arrowhead at end. Provides context beyond schema.

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

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

Clearly states verb 'create' and resource 'connector (arrow or line)'. Distinguishes from siblings by specifying target: 'FigJam' connectors, linking nodes or canvas positions. 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?

Provides clear usage context: 'draw flow arrows between stickies, shapes, etc.' Does not explicitly exclude alternatives, but among many create siblings, this tool is distinct. Lacks explicit when-not-to-use, but context is sufficient.

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. It only states the basic action without mentioning side effects (e.g., whether existing styles are overwritten, required permissions, or response behavior). This is insufficient for a creation tool.

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

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

The description is a single, front-loaded sentence with no wasted words. Every element is relevant.

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

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

For a tool that creates a resource (effect style), the description lacks crucial context: return value (likely style ID), uniqueness constraints, potential errors (e.g., duplicate name), and performance considerations. No output schema is present, so the description should compensate.

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 covers 100% of parameters, so the description adds little value beyond mentioning 'shadows, blurs' as examples. It does not elaborate on parameter usage or constraints beyond what the schema already 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 ('create'), the resource ('a reusable effect style'), and the domain ('Figma's local styles'). It specifies the types ('shadows, blurs'), effectively distinguishing it from sibling tools like create_paint_style or create_text_style.

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 reusable styles rather than applying effects to individual nodes, but it does not explicitly compare with alternatives like set_effects or set_effect_style_id, nor does it provide when-not-to-use guidance.

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

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

There are no annotations, so the description must fully disclose behavior. It only states that an ellipse is created, but fails to mention whether the ellipse is added to the selection, any side effects on the document state, or requirements like the parent parameter being mandatory.

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 too short, consisting of a single sentence. While concise, it omits critical information, making it too sparse to be truly helpful.

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 9 parameters and many sibling tools, the description is incomplete. It does not explain return values, how the ellipse relates to the canvas, or any interactions with other tools like setting properties.

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 no extra meaning beyond what the schema provides, such as clarifying coordinate systems or color formats.

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 new ellipse in Figma', which is a specific verb+resource. However, it does not differentiate from sibling tools like create_rectangle or create_polygon, which similarly create 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?

No guidance is provided on when to use this tool vs alternatives. The description does not mention prerequisites, such as needing a parentId from get_pages, nor does it exclude cases where other shape tools would be more appropriate.

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 only states 'Create a new frame.' It does not mention side effects, authentication needs, return values, or potential limitations. The schema hints at required fields, but that's not sufficient.

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 single-sentence description is concise and front-loaded, but given the tool's complexity (9 parameters, nested objects), slightly more detail could be beneficial without losing 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 no annotations and no output schema, the description is too sparse. It does not explain what the tool returns, how to use it in a workflow, or any constraints beyond the schema. The schema helps, but the description should provide more 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?

Schema description coverage is 100%, providing detailed parameter descriptions (e.g., coordinate system, parent ID requirement). The tool description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description 'Create a new frame in Figma' clearly states the verb and resource, distinguishing it from sibling tools like create_rectangle or create_ellipse. However, it lacks specificity about the frame's role as a container or its relationship to other elements.

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 (e.g., create_rectangle, create_section). The schema contains a note about parentId being required, but the description itself offers no usage context 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?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It does not mention side effects, output, limits, or whether the new page becomes active. For a create operation, more transparency is needed.

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 communicates the purpose without any extraneous words. Every part is 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?

Given the absence of an output schema and annotations, and the presence of many sibling tools, the description is too minimal. It does not explain what 'current Figma document' implies or what the result of creation is, leaving gaps for a new user.

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 the parameter 'name' described. However, the description adds no extra context such as naming conventions, uniqueness, or character limits. Baseline score of 3 is appropriate.

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

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

The description clearly states the action (create), the resource (page), and the scope (in the current Figma document). It differentiates from sibling tools like delete_page, duplicate_page, and rename_page by focusing solely on creation.

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 (e.g., duplicate_page or organize_pages). There is no mention of prerequisites or situations where creation is not appropriate.

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, and the description lacks details on side effects, error behavior (e.g., duplicate names), permissions, or return value. It only states that it creates a style, which is minimal transparency.

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 front-loads the action and resource. Every word is meaningful 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 output schema or annotations, the description should ideally mention return values or potential errors. It is adequate for a simple creation tool but incomplete regarding behavioral 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 input schema covers all 5 parameters with descriptions (100% coverage). The description adds value by specifying 'SOLID' type, which clarifies that only solid color styles are created, not gradients or other paint 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 clearly states the action ('Create'), the resource ('reusable color/paint style'), and the type ('SOLID') in Figma's local styles. It distinguishes itself from other style creation tools like create_effect_style or create_text_style.

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 does not provide any guidance on when to use this tool versus alternatives like create_effect_style or create_text_style. No context on prerequisites or limitations 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?

No annotations are provided, and the description gives no behavioral details such as side effects, permissions, or constraints beyond what is in parameter descriptions. The parameter description for parentId hints at requirement, but that is parameter-level info.

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 (5 words), which is efficient, but it lacks substance for a tool with 10 parameters. It could be expanded without losing 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?

No output schema exists, and the description does not explain return values or side effects. With 10 parameters including nested objects, the description is incomplete 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 coverage is 100%, so baseline is 3. The description does not add meaning beyond the schema; however, the schema itself provides clear parameter descriptions, so no deduction needed.

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

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

The description 'Create a new polygon in Figma' clearly states the verb and resource, but lacks differentiation from sibling tools like create_star or create_ellipse. It is specific but could be more distinctive.

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. The description does not mention prerequisites, limitations, or context, 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?

No annotations are provided, and the description only says 'Create a new rectangle'. It does not disclose behavioral traits such as side effects (e.g., selection changes, file modification), required permissions, or 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 one sentence, concise and front-loaded. However, it could include more contextual hints without becoming verbose, so a 4 is suitable.

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

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

Given the tool has 9 parameters and nested objects, the description is minimal. It lacks context about the working file, selection, or output. No mention of return values or required state.

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

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

The schema description coverage is 100%, so the schema already documents all parameters. The description adds no extra meaning beyond the schema. 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 action 'Create', the resource 'rectangle', and the platform 'Figma'. It is specific and distinguishes this tool from siblings like create_ellipse or create_frame.

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 (e.g., create_shape_with_text, clone_node). It does not mention prerequisites or when not to use it.

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

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

No annotations are provided, so the description must carry the full burden. It only states that sections appear as labelled coloured regions, but does not disclose behavioral traits such as side effects, permission requirements, or what happens when optional parameters are omitted.

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, with the first sentence stating the action and the second explaining the purpose. It is concise and front-loaded with no wasted words.

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

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

Given the tool has 7 parameters, 2 required, and no output schema, the description is incomplete. It omits critical context such as the parentId requirement, default values for width/height, and what the tool returns. Siblings are not mentioned for contrast.

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 adds no additional meaning beyond the schema for any parameter; it is a high-level overview without per-parameter elaboration.

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 FigJam section' with a specific verb and resource, and explains that sections are used to group and organize content as labelled coloured regions. It distinguishes from sibling tools like create_rectangle or create_sticky by defining the unique purpose of sections.

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 vs alternatives (e.g., group_nodes or frames). It does not mention prerequisites like the need for a parentId, which is described as required in the schema but not highlighted.

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 adds key behavioral info: 'parentId' is required server-side despite not being in required array, and lists supported shapes. However, it omits details on mutation behavior, undo, or authentication needs.

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

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

Two concise sentences with no filler. Front-loaded with verb and purpose, followed by essential list of supported shapes. Every sentence earns its place.

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

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

Despite 9 parameters and no output schema, the description is minimal. It fails to explain coordinate system, default dimensions, text rendering behavior, or error cases. ParentId requirement is mentioned but could be clearer. More context needed for a complex 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%, so baseline is 3. The description lists shape enum values and mentions text inside, adding marginal value over schema. No additional parameter semantics beyond what schema already provides.

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

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

The description clearly states the tool creates a FigJam shape with text inside, using specific verb 'Create' and resource 'shape with text'. It distinguishes from sibling shape tools (e.g., create_rectangle, create_ellipse) by emphasizing text inclusion and listing supported 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?

The description notes usefulness 'for flowcharts, diagrams, and process maps', providing clear usage context. It implies when to choose this tool over shape-only siblings, but lacks explicit when-not-to-use or alternative recommendations.

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

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

No annotations exist, so the description carries full responsibility. It fails to disclose side effects, required permissions, return value, or whether the operation is reversible, leaving significant 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, concise and to the point. However, it could include more context without becoming verbose, so it earns a 4 rather than 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?

Given 11 parameters, nested objects, and no output schema, the description is too sparse. It does not explain return behavior, restrictions, or lifecycle implications, making it incomplete for an autonomous 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% with good descriptions. The description adds value for parentId by clarifying it is required and suggesting get_pages for page IDs, but overall adds little beyond the schema.

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

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

The description clearly states the verb ('Create') and resource ('a new star in Figma'), distinguishing it from sibling tools like create_rectangle or create_ellipse.

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 when-to-use or when-not-to-use guidance is given. The description provides a hint about parentId requirements, but does not address selection among similar shape-creation tools.

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

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

No annotations are provided, so the description must fully disclose behavior. It only states creation and primary use for text. Critical details like the required parentId (enforced server-side) are not mentioned, nor any mutation implications or 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?

Two sentences, front-loaded with the core action and context. No wasted words.

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 thorough schema descriptions and no output schema, the description covers basic purpose but lacks mention of important constraints (e.g., parentId requirement) that are only in the property descriptions. It could provide more integration context with sibling 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 coverage is 100% with descriptions for all parameters. The main description adds no additional semantic meaning beyond the schema, so 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 'Create a sticky note in a FigJam board' and notes that sticky notes are the primary way to add text content. However, it does not differentiate from sibling tools like create_text or create_shape_with_text, which also add text.

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. The description implies sticky notes are primary for text, but does not specify exclusions or provide when-not-to-use advice.

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 should carry behavioral context. It only states the basic action, omitting important details like side effects, requirements (e.g., parentId), or the need to load fonts first.

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. It could benefit from slightly more structure (e.g., a brief list of required inputs), but it is not verbose.

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

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

Given the tool's complexity (11 parameters, no output schema or annotations), the description is insufficient. It fails to mention critical context like the required parentId or the need to use load_font_async first.

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 no additional parameter meaning beyond the schema descriptions, which are already detailed.

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 resource (text element) in Figma. It is specific and directly conveys the tool's function, though it does not differentiate from sibling create tools.

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

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

The description provides no guidance on when to use this tool versus alternatives like create_shape_with_text or other create tools. It lacks any context about prerequisites or typical usage 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?

No annotations are provided, so the description must compensate. It only states the tool creates a style, but doesn't disclose behavior like whether it overwrites existing styles, requires permissions, or returns the style ID. For a create operation, expected mutation is implied, but more detail is needed.

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 with no wasted words. The first sentence immediately states the action and target, making it front-loaded and efficient.

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

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

Given the tool has 10 parameters and no output schema, the description should explain what the created style yields (e.g., style ID for later use) and any constraints (e.g., file context). The current description is too minimal for effective use.

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

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

The input schema has 100% coverage with clear parameter descriptions, so the description adds no additional semantic value. Baseline 3 is appropriate; the description could have clarified defaults or relationships between parameters (e.g., lineHeightUnit affecting how lineHeight is interpreted).

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 reusable text style in Figma's local styles, which is distinct from other style creation tools (e.g., create_effect_style). However, it doesn't explicitly differentiate from sibling tools like create_paint_style, but the context 'text style' makes it sufficiently 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 guidance on when to use this tool vs. alternatives (e.g., using set_text_style_id or creating a text node with inline styles). The description only mentions 'useful for design system consistency,' which is a general benefit, not a usage guideline.

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 bears the full burden of behavioral disclosure. It only states the basic delete action and omits critical traits such as irreversibility, whether child nodes are deleted, or any side effects. For a destructive operation, this is a significant transparency 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, direct sentence with no filler words. It is front-loaded with the action and resource, but it is so minimal that it omits useful behavioral context; still, as far as structure and brevity, it is clean.

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 tool with no annotations and no output schema, the description is incomplete. It fails to mention the irreversible nature of the operation, whether children are affected, or how this tool differs from 'delete_multiple_nodes'. An agent is left without key information for safe 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 100% and the 'nodeId' parameter is clearly described as 'The ID of the node to delete'. The tool description does not add extra parameter semantics beyond the schema but does not need to, so the 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?

The description states a specific verb ('Delete'), a resource ('node'), and a context ('from Figma'), making the core action clear. It does not explicitly differentiate from the sibling tool 'delete_multiple_nodes', so the specificity is slightly incomplete, but the singular phrasing and tool name carry that distinction.

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 about when to use this tool versus alternatives such as 'delete_multiple_nodes'. The description gives no context for choosing between single and batch deletion, nor 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?

No annotations exist, so description must disclose behavioral traits. It only states the action without mentioning consequences (permanent deletion, permissions needed, impact on other pages). Insufficient for a destructive 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?

Single sentence with no wasted words. Efficiently communicates the core function despite brevity.

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 tool (1 param, no output schema), the description is minimally adequate. Does not explain return value or error scenarios, but acceptable for low 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 coverage is 100% and the parameter description in schema already explains the parameter. The tool description adds no extra meaning, so baseline score of 3 is appropriate.

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

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

Description clearly states the action (delete) and the resource (page) with context (from current Figma document). Distinguished from sibling 'delete_node' which deletes a node within a page.

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 (e.g., delete_node). Missing prerequisites or conditions like whether the page can be current or the last page.

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

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

The description explains the primary behavioral change (breaking link, converting to frame) but lacks details on irreversibility, effect on overrides, or required permissions. No annotations to supplement, so description carries full burden.

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

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

The description is a single sentence with no wasted words, efficiently conveying the tool's purpose and effect.

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

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

Given the tool's simplicity (one parameter, no output schema), the description is fairly complete. It covers the core functionality, though it could mention error cases or that the instance must exist. Overall, adequate.

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

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

The single parameter instanceId is described in the schema ('The ID of the instance to detach'), and the tool description does not add additional meaning. Schema coverage is 100%, so baseline score of 3 is appropriate.

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

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

The description clearly states the action (detach a component instance) and the outcome (convert to regular frame, break link with main component). It is specific and distinguishes from sibling tools like create_component_instance or set_instance_variant.

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 (when you want to break the component link) but does not provide explicit guidance on when not to use or mention alternatives. No context on prerequisites or side effects.

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 alone must disclose behavior. It states a complete copy is made, but does not detail side effects (e.g., page position, naming collision handling beyond default, undoability). Basic transparency but insufficient 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?

Single sentence with no wasted words. Clearly communicates the tool's action and result. 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?

No output schema and no annotations. Description lacks details on where the duplicate is placed, whether it's reversible, error handling for invalid pageId, or how it relates to siblings like clone_node. Incomplete for a side-effect 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 has 100% coverage for both parameters. Description adds no extra meaning to parameter semantics; it only explains the overall effect. Baseline score of 3 is appropriate.

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

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

The description clearly states the verb 'Duplicate' and resource 'an existing page', and specifies the result as 'creating a complete copy of all its contents'. It distinguishes from siblings like create_page (creates empty page) and clone_node (clones a node).

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 like clone_node or create_page. The purpose is straightforward, but the description lacks context about prerequisites or 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 provided, the description carries the full burden of behavioral disclosure, but it only restates the tool name without adding behavioral context. It does not state whether the operation is read-only, what response format to expect, what limits exist, or how unsupported nodes are handled.

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 one short, front-loaded sentence with no wasted words. It is easy to parse, though the brevity sacrifices useful behavioral context.

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 and no output schema, so the description is the only place to communicate return behavior, side effects, and constraints. It provides none of that, leaving an agent uncertain about what happens after invocation beyond the parameter contract.

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 already documents all three parameters adequately. The description adds no additional meaning to nodeId, scale, or format beyond what the schema provides, which aligns with the baseline of 3.

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 ('Export'), resource ('a node'), and result ('as an image'), making the core purpose clear. It is distinct from sibling tools, though it does not explicitly differentiate itself from alternatives by name.

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 siblings, no prerequisites, and no mention of exclusions or alternatives. Usage is only implied by the tool's purpose, not explained.

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, and the description does not disclose behavioral traits such as mutation, destructiveness, permissions, or side effects. The minimal description offers insufficient transparency.

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 (14 words) and front-loaded with the main action, though it could be slightly more structured.

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

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

Given the tool's simplicity (one param, no output schema, no annotations), the description provides core purpose but lacks details on outcomes, error conditions, or prerequisites, leaving some gaps 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% with a single parameter described as 'ID of the node to flatten'. The description adds no extra meaning beyond the schema, but the parameter is self-explanatory.

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 ('flatten a node') with examples (boolean operations, converting to path), distinguishing it from siblings like 'boolean_operation' (a specific operation type) and 'convert_to_frame'.

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 examples of when to use (boolean operations, converting to path) but lacks explicit guidance on when not to use, prerequisites (e.g., node type), or alternatives.

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

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

No annotations are provided, so the description must bear the burden of behavioral disclosure. It only states it reads annotations, but does not address edge cases (e.g., node not found, no annotations), response format, or any limitations related to the proposed API.

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 short (two sentences) with no redundancy. The second sentence about the proposed API is slightly extraneous but does not detract from clarity.

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

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

With no output schema, the description should at least hint at the return format or contents of annotations. It fails to do so, leaving the agent uncertain about what to expect. Additionally, the mention of a 'proposed' API suggests instability but lacks further 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 input schema covers 100% of parameters with a description for nodeId. The description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool reads annotations from a node, distinguishing it from sibling tools like set_annotation that write. The verb 'read' and resource 'annotations' are specific, but it could be more explicit about the context of annotations.

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

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

The description provides no guidance on when to use this tool versus alternatives. While set_annotation exists as a sibling for writing, the description does not mention it or provide any when-to-use or when-not-to-use advice.

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. 'Get' implies a read operation, but the description does not state whether there are side effects, authentication requirements, or any details about what 'detailed information' includes or how it is returned.

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. It front-loads the action and resource clearly, earning its place without redundancy.

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

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

For a parameterless tool, the description is minimally adequate, but it leaves the agent without a clear sense of what 'detailed information' means or what the output will contain. With no output schema and no annotations, more specificity about the returned content would make it complete.

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

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

The tool has zero parameters, so the schema already fully covers this dimension. The description adds no parameter semantics, but none are needed for a parameterless tool; the baseline of 4 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 'get' and the resource 'current Figma document,' which identifies the tool's function. However, 'detailed information' is vague and does not specify what is included, and it doesn't explicitly distinguish itself from sibling tools like get_node_info or read_my_design.

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_selection, get_node_info, or read_my_design. The description gives a general purpose but no context, exclusions, or selection criteria, 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?

No annotations are provided, so the description carries the full burden. It states it reads contents but does not disclose behavioral details (e.g., whether the tool is read-only, what happens if the page is not a FigJam board, or performance characteristics). The description is adequate but lacks depth.

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: first explains what elements are retrieved, second when to use. Front-loaded, no filler, 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 no parameters and no output schema, the description provides sufficient context for a simple read operation. It lists the element types and board context. It could mention the output structure (e.g., returns an array) but is not required to be exhaustive.

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

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

No parameters exist, so schema coverage is 100% trivially. Per guidelines, 0 parameters warrants a baseline of 4. Description adds no parameter semantics, which is acceptable here.

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

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

Description clearly states it retrieves FigJam-specific elements (stickies, connectors, shapes with text, sections, stamps) on the current page, distinguishing it from general node retrieval tools like get_node_info 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 recommends using this tool to read FigJam board contents, providing clear context. Lacks explicit alternatives or when-not-to-use guidance, but the sibling list implies alternatives like get_node_info for broader node data.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Read' (non-destructive) but fails to mention error handling, permissions, or what happens if the node is not a frame. This leaves significant gaps for an agent.

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 that front-loads the action ('Read layout grids from a frame node in Figma'). Every word is meaningful with no unnecessary fluff.

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

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

Given the tool's simplicity (1 parameter, no output schema), the description is minimally adequate but lacks details about return format or behavior when the node has no grids. It covers the core functionality.

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% (the only parameter 'nodeId' is described in schema). The description adds no additional meaning beyond 'The ID of the frame node to read grids from', so 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 'Read layout grids from a frame node in Figma' uses a specific verb ('Read') and identifies the resource ('layout grids'), clearly distinguishing it from sibling tools like 'set_grid' (write) and 'get_guide' (guides vs grids).

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 reading grids from a frame node but provides no explicit guidance on when to use vs alternatives or prerequisites (e.g., node must be a frame). The purpose is clear enough for the agent to infer basic 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 provided, the description must disclose behavior. It correctly implies a read operation but does not mention permissions, side effects, or return format. The description is insufficient for a mutation-free tool.

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

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

The description is concise (five words) and front-loaded. It has no wasted words, but the extreme brevity may sacrifice necessary detail, making it less than ideal.

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 only one parameter and no output schema, but the description fails to explain what guides are or how they relate to sibling tools like grids. The context is incomplete for effective use.

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

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

Schema coverage is 100% (one parameter with description). The tool description adds no additional meaning beyond the schema, so a baseline of 3 is appropriate.

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

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

The description states 'Read guides from a page', providing a clear verb and resource. However, it does not differentiate from sibling tools like get_grid or get_annotation, leaving ambiguity about what 'guides' refers to (e.g., ruler guides vs. grid guides).

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 alternatives such as set_guide, get_grid, or get_annotation. The description does not mention prerequisites or context.

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

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

No annotations provided, so description carries full burden. It only states 'extract image metadata' without detailing what metadata is returned, behavior on non-image nodes, or error conditions. Inadequate for 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?

Single sentence is extremely concise and front-loaded with the core action. No wasted words.

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

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

Given no output schema and only one parameter, description should specify what 'image metadata' includes (e.g., dimensions, format). Current description leaves ambiguity, making it incomplete for effective tool use.

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

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

Schema description coverage is 100% (nodeId described as 'The ID of the node'). Description adds no additional parameter semantics beyond schema, so baseline score of 3 is appropriate.

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

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

Description uses specific verb 'Extract' and resource 'image metadata from a node', clearly distinguishing from sibling tools like 'export_node_as_image' or 'get_svg' which handle actual image data.

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

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

No explicit guidance on when to use this tool versus alternatives. While the purpose is clear, there is no mention of prerequisites, context, or exclusion cases.

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

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

No annotations are provided, so the description carries the full burden. It clearly signals a read-only list operation via 'Get,' but it does not define what qualifies as 'local,' whether nested/variant components are included, or what the returned component data contains.

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 filler. Every word adds value, and the key scoping terms 'local' and 'Figma document' are included.

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 getter, the description is mostly sufficient to invoke the tool correctly. However, with no annotations and no output schema, the agent is left to infer the exact return structure and the precise boundary of 'local components.'

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 there is no schema to elaborate on and no parameter meaning to clarify. Baseline 4 applies because no input documentation is needed.

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

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

The description states a specific verb and resource: 'Get all local components' scoped to 'the Figma document.' It is clear and distinguishable from siblings like get_selection, get_styles, or get_node_info, though it does not explicitly name an alternative.

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

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

There is no explicit guidance about when to use this tool instead of related tools like scan_nodes_by_types or get_styles. The term 'local' implies it excludes library/team components, but this distinction is 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?

No annotations are provided, but the description does not disclose what 'detailed information' includes, such as properties or children. The depth parameter hints at nested detail, but overall behavioral traits are 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 with no waste. It could be slightly more informative without losing 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?

Without an output schema, the description should explain what data the tool returns. It does not, leaving the agent uncertain about the response structure. Incomplete for a retrieval 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%, so the schema already documents both parameters well. The description does not add significant meaning beyond 'specific node', earning a baseline score of 3.

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 detailed information about a specific node in Figma', using a specific verb and resource. It distinguishes from siblings like get_document_info and get_nodes_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?

No guidance on when to use this tool versus alternatives (e.g., get_nodes_info for multiple nodes). The description offers no when-to-use or when-not-to-use context.

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

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

No annotations provided, so description must disclose behavior. It only says 'detailed information' without describing what 'detailed' means, how depth parameter affects results, or any side effects. Lacks transparency on return structure or limitations.

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

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

Extremely concise single sentence, front-loaded with key purpose. No redundant 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?

Given no output schema and two parameters, the description could be more complete by explaining the return value or depth behavior. But schema covers parameter details, so it's minimally adequate.

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

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

Input schema already documents both parameters with descriptions (100% coverage). The description adds 'detailed information' but no additional semantic meaning beyond the schema.

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

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

Description clearly states 'Get detailed information about multiple nodes in Figma', which is a specific verb-resource combination. It distinguishes from the singular get_node_info sibling by implying multiple nodes, though not explicitly stating the plural nature.

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 get_node_info or other query tools. Does not specify context, prerequisites, or exclusions.

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

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

With no annotations, the description carries full burden but only states the basic action. Does not disclose if pages include hidden/archived pages, authorization requirements, or performance implications.

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

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

One sentence, no wasted words, appropriately sized for the tool's simplicity.

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

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

For a simple getter with no parameters and no output schema, the description is fairly complete. However, lacks detail on what 'all pages' entails (e.g., hidden pages, order).

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, so schema coverage is 100%. Baseline score of 4 applies; the description adds context by specifying 'in the current Figma document', which is clear.

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

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

The description clearly states the verb 'Get' and resource 'all pages' with scope 'in the current Figma document'. It is specific and distinguishes from sibling tools like 'create_page' and 'delete_page'.

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. There is no mention of prerequisites, filtering, or when not to use it.

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

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

With no annotations, the description carries the burden of disclosing behavior. It correctly indicates the tool is read-only (no mutation). It does not detail side effects or permissions, but for a simple read operation, this is adequate. No contradictions.

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

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

The description is two sentences, front-loading the action and resource. Every sentence adds value, with no unnecessary words. It is optimally 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?

Given the tool's simplicity (one parameter, no output schema, no nested objects), the description provides sufficient context: it states the action, resource, and typical use case. It could briefly mention the return format (array of reactions), but not having it does not hinder understanding significantly.

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

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

The input schema has 100% coverage with a description for nodeId. The tool description does not add any additional meaning beyond the schema's description, so it meets the baseline but does not exceed it.

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

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

Description clearly states the tool reads prototype interactions (reactions) from a node, with a specific verb (read) and resource (interactions from a node). It also distinguishes from the sibling write tool set_reactions by emphasizing read-only purpose.

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

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

The description mentions the tool is 'useful for debugging and inspecting existing interactions,' implying when to use it, but it does not explicitly state when not to use it or provide alternatives (e.g., set_reactions for writing). Guidance is implied but not comprehensive.

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 fully disclose behavioral traits. It only states the operation is a read ('Get') but does not mention authentication requirements, library selection, or what 'available' entails (e.g., published vs. unpublished). Minimal transparency beyond the basic action.

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, concise sentence that is front-loaded with the verb and resource. No extraneous information, every word contributes to understanding 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?

Given the simplicity (no parameters, no output schema), the description is adequate but could be more complete by clarifying that it retrieves published components from accessible team libraries. The lack of output schema increases the need for description of return value scope.

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 zero parameters and 100% schema coverage, the description does not need to explain parameters. It adds value by specifying the resource ('team libraries'), which is not evident from the empty schema. Baseline 4 for zero parameters 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 'Get' and the specific resource 'available components from team libraries in Figma'. It distinguishes itself from the sibling tool 'get_local_components' by specifying 'remote' components, making its purpose precise and unambiguous.

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

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

The description implies usage for retrieving team library components but does not explicitly state when to use this tool versus alternatives like 'get_local_components'. No exclusions or conditions are provided, leaving the agent to infer context.

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

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

With no annotations provided, the description must carry the behavioral disclosure burden. It signals a read operation through 'Get information' but does not disclose return fields, side-effect freedom, or any prerequisites like needing an open document. This is minimal extra value beyond the tool's name.

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 filler or redundancy. Every word contributes to stating 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?

This is a simple zero-parameter getter, so the description is nearly sufficient. However, with no output schema present, the vague term 'information' leaves the agent guessing about the return shape, such as whether it returns node IDs, types, or names.

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 and schema coverage is effectively complete, so the description has nothing to add. The baseline of 4 applies because no parameter semantics are needed.

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

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

The description states a clear verb ('Get') and resource ('current selection in Figma'), making the tool's basic purpose understandable. It is distinct from siblings such as set_selections, get_node_info, and get_document_info, though it does not enumerate exactly what information is returned.

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 when-to-use or alternative tool guidance is provided. The name and sibling list imply it is for reading the active selection rather than mutating it with set_selections or querying a specific node with get_node_info, but this is left 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?

No annotations are provided, so the description carries full burden. However, it only states the function without disclosing behavioral traits such as what happens with invalid nodeId, whether it is a read-only operation, or if there are any side effects. The simplicity leaves ambiguity about error handling and output nature.

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

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

The description is a single, direct sentence with no extraneous information. It is appropriately sized for the tool's simplicity and front-loaded with the core action.

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 lack of output schema and annotations, the description omits details about return format, pagination, or error behavior. While the tool is simple, the description is minimally adequate but leaves gaps that could be filled with more 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?

Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides; it merely restates the purpose without elaborating on parameter values or usage nuances.

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 gets text segments with specific styling within a text node. The verb 'Get' and resource 'text segments with specific styling' are specific. Among siblings, 'scan_text_nodes' is broader, so this tool is clearly distinguished.

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 needing to analyze styled segments in a specific text node, but it does not provide explicit instructions on when to use this tool versus alternatives like 'scan_text_nodes' or 'get_node_info'. No when-not or prerequisites 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 carries the full burden of behavioral disclosure. It only says 'Get', implying a read operation, but does not clarify what kinds of styles are included (fill, text, effect, grid), whether library styles are returned, or what the response contains. This is minimal behavioral detail.

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 filler. Every word earns its place, and the verb-resource-scope structure makes it easy to parse quickly.

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

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

For a simple zero-parameter getter, the description is largely sufficient: an agent knows what action to take and what resource to expect. The main gap is the ambiguous scope of 'styles', which could be interpreted in multiple ways, but the overall call is straightforward.

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 schema requires no documentation. The baseline of 4 applies because there are no parameter semantics to clarify; the description does not need to add parameter-level meaning.

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 ('Get'), a clear resource ('all styles'), and a scope ('current Figma document'). It is immediately distinguishable from sibling tools like get_local_components or get_document_info, which target different resources.

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_local_components or get_document_info. The phrase 'from the current Figma document' gives some context, but no explicit conditions, exclusions, or alternative-tool routing are provided.

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

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

With no annotations provided, the description carries full burden. It states the output (SVG string with all nested children) and the action (export). However, it does not disclose any side effects, permissions, or limitations such as whether this triggers rendering or has size constraints.

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, concise and front-loaded with the core purpose. Every word adds value, with no filler or redundancy.

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

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

For a simple export tool with one required parameter and no output schema, the description is mostly complete. It explains what is returned (SVG markup including children). Missing are potential error conditions or limitations, but overall adequate.

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

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

Schema coverage is 100% with a single required parameter 'nodeId' described as 'The ID of the node to export as SVG'. The description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool exports a single node as an SVG string from Figma, with specific verb 'export' and resource 'node as SVG'. It distinguishes itself from sibling tools like 'export_node_as_image' and 'get_image_from_node' by specifying the output format (SVG) and including nested children.

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 obtaining SVG markup of a node but does not explicitly mention when to use this tool over alternatives like 'export_node_as_image' or 'get_image_from_node'. No exclusion or alternative guidance is provided.

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

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

The description indicates a read-only operation ('list... returns'), which is sufficient. No annotations exist, but the description carries the full burden and does not contradict any structured data.

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?

One sentence that is front-loaded with the key action and resource, no wasted words.

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

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

With zero parameters and no output schema, the description completely explains what the tool does and returns, making it fully sufficient 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?

There are no parameters, so schema coverage is 100%. The description adds meaning beyond the schema by describing the return structure (collections, modes, variables).

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 'list' and the resource 'variable collections and their variables', and it differentiates from sibling tools like 'apply_variable_to_node' or 'set_variable'.

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 when-to-use or alternatives are mentioned, but for a simple read-only listing tool, the usage context is implied given sibling tools are mostly mutation or specific manipulators.

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 but merely states the action. It does not disclose whether grouping is destructive, requires selection, or affects existing groups, leaving the agent uninformed.

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 (4 words), which is efficient, but lacks any explanatory structure. It earns a high conciseness score but could benefit from minimal elaboration.

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 simplicity (2 params, no output schema), the description is too minimal. It does not explain the effect of grouping, side effects, or expected behavior, leaving gaps 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% (both parameters have descriptions in the schema). The description adds no extra meaning beyond what the schema already provides, so 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?

The description 'Group nodes in Figma' clearly states the action (group) and resource (nodes), distinguishing it from siblings like 'ungroup_nodes', 'flatten_node', and 'delete_node'.

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. The description does not indicate when to use this tool over alternatives, nor does it mention 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?

No annotations provided, and the description does not disclose behavioral traits such as whether this is a destructive operation, auth requirements, or side effects on the document. The bare verb 'insert' leaves much to the agent's assumption.

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, concise sentence that front-loads the essential information. No superfluous words.

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, no annotations, and a moderate number of parameters (3), the description is incomplete. It does not explain return values, error conditions, or the effect on the document structure. The agent may lack sufficient context for 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 100%, so the baseline is 3. The description does not add any extra meaning beyond what is already in the schema; it merely repeats the operation. No parameter details are given.

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 (insert) and the target resource (child node inside a parent node), which is distinct from sibling tools that perform other operations like delete, move, or rename.

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 move_node or duplicate_node. No mention of prerequisites or when not to use it.

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

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

Annotations are absent, so the description must disclose side effects, permissions, or state changes. It only says 'join' and 'communicate', with no indication of what happens upon joining, whether it's reversible, or if any permissions are required. This is insufficient 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 very short (one sentence), which risks under-specification. While it avoids fluff, it omits crucial details, making it less effective. It is concise but incomplete.

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 lack of annotations and output schema, the description should provide more context about return values, side effects, and prerequisites. For a state-changing tool like 'join_channel', this description is inadequate.

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

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

The input schema already describes the sole parameter ('channel') with full coverage (100%). The description adds no additional semantic value beyond what the schema provides, so a score of 3 is appropriate.

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

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

The description clearly states the action (join) and the resource (channel). However, the phrase 'to communicate with Figma' is vague; it doesn't specify what joining a channel entails. Nonetheless, the core purpose is evident and distinct from sibling tools.

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

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

No guidance is provided on when to use this tool versus alternatives. For instance, there is a sibling 'list_active_channels' that might be a prerequisite, but no hints are given. The description offers no 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?

The async nature is mentioned, but no details on return behavior, error handling, or side effects. With no annotations, the description should provide more 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?

A single sentence that is entirely non-redundant and front-loaded with key information. No unnecessary words.

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 file loading operation with no output schema, the description lacks critical context about async behavior, error states, and usage prerequisites. Minimal completeness.

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

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

Schema coverage is 100%, so the description adds no extra meaning beyond what the schema already provides. Baseline score 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 action (load) and resource (font) with the async qualifier. It is distinct from sibling tools like set_font_name which modify properties rather than loading.

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, or prerequisites such as font availability. The description lacks context for decision-making.

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, and the description does not disclose behavioral traits like side effects, permissions required, or coordinate system behavior. It only states the basic action without deeper 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, concise sentence that gets straight to the point with no unnecessary words.

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

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

With no output schema and no annotations, the description fails to explain return values or provide complete context for using the tool effectively. It is minimal.

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 already provides clear parameter meanings. The description adds no extra semantic value beyond what is in 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 'Move a node to a new position in Figma,' using a specific verb and resource. It effectively distinguishes this tool from siblings like 'resize_node' and 'rotate_node'.

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 lacks information about prerequisites, limitations, or conditions under which moving a node might not be appropriate, such as within auto-layout frames.

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, and the description does not disclose behavioral traits such as whether the rename is destructive, if it requires permissions, or what happens to the node's children or styles. For a mutation tool, this is a significant lack of transparency.

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 is concise and to the point, with no extraneous information. It is efficient but lacks any structural elements like bullet points or sections.

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 output schema, so the description should ideally explain what is returned (e.g., success confirmation, updated node ID). It does not. Also, annotations are missing. For a simple two-parameter tool, it is marginally adequate but 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 coverage is 100% with clear descriptions for both parameters (nodeId and name). The description adds no extra meaning beyond what the schema already provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states the verb 'rename' and the resource 'node', and lists specific node types (frame, component, group, etc.), making it easy to distinguish from sibling tools like 'move_node' or 'delete_node'.

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 'set_node_properties', which might also allow renaming. The agent has no help in deciding between these tools.

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

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

With no annotations, the description carries full responsibility for behavioral transparency. It reveals that the tool mutates the document by renaming a page, but does not disclose side effects, such as impact on nested elements or potential name conflicts. No read-only or destructive hints 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 a single, front-loaded sentence that efficiently conveys the core action. It is concise with no redundant words, though it could include brief context without becoming verbose.

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

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

For a simple two-parameter tool with no output schema, the description is minimally adequate. However, it lacks completeness on preconditions (e.g., page must exist) and postconditions (e.g., name change affects references), which would help an agent avoid errors.

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

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

The input schema has 100% coverage with clear descriptions for both parameters ('ID of the page to rename' and 'New name for the page'). The tool description adds no additional meaning beyond the schema, meeting the baseline for full schema coverage.

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

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

The description clearly states it renames an existing page in the Figma document. The tool name and description together specify the resource (page) and action (rename). However, it does not explicitly differentiate from the sibling tool 'rename_node', which could rename any node, leaving potential ambiguity.

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

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

No guidance is provided on when to use this tool versus alternatives like 'rename_node' or 'create_page'. There is no mention of prerequisites, such as the page needing to exist, 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 burden. It discloses that the tool changes layer order within the same parent, which is a non-destructive operation. It does not mention any side effects, permissions, or error conditions, but for this simple tool, the behavior is adequately transparent.

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, consisting of two short sentences that immediately convey the core purpose and key distinction. No unnecessary 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?

Given the tool's simplicity (3 parameters, no output schema), the description covers all necessary aspects: purpose, distinction from a key sibling, and interaction between parameters. The agent has enough context to select and invoke the tool correctly.

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

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

The input schema has 100% description coverage for all parameters. The description adds value by clarifying that the 'index' parameter overrides 'position' if both are provided, which is not stated in the schema. This helps the agent understand parameter precedence.

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 explicitly states the tool changes the z-order of a node within its parent, using a specific verb ('Change') and resource ('z-order of a node'). It clearly distinguishes itself from 'insert_child' by noting that reorder_node does not re-parent.

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

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

The description explicitly contrasts with 'insert_child' to guide when to use this tool vs that sibling. However, it does not mention other related siblings like 'move_node' (which changes position in 2D space) or provide explicit when-not-to-use guidance, leaving some ambiguity.

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 notes that transform is preserved, which is useful, but omits other traits like what happens if no existing image, auth needs, or side effects. The description adds some context beyond the name but is 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 a single sentence that is direct and efficient, containing no redundant or irrelevant information. Every word contributes.

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 tool with no output schema and no annotations, the description is somewhat sparse. It covers the core action but lacks details on transform preservation semantics, error conditions, or the return value. It is minimally adequate.

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

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

Schema coverage is 100%, so each parameter is already described in the schema. The description adds no additional parameter-specific meaning beyond what the schema provides. The baseline of 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?

The description "Replace existing image on node with new image while preserving transform" clearly states the action (replace) and the resource (image on node). It provides a specific verb and resource, distinguishing it from generic set operations. However, it does not explicitly differentiate from the sibling tool 'set_image_fill'.

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 you want to replace an image while keeping its transform, but it provides no explicit guidance on when to use this vs. alternatives like set_image_fill, nor does it mention prerequisites or when not to use.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Resize a node in Figma' only implies mutation; it does not disclose whether the operation is reversible, how it interacts with auto-layout, constraints, or child nodes, or any side effects. For a mutating tool with zero annotation coverage, this is a significant gap.

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

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

The description is a single front-loaded sentence with zero filler: 'Resize a node in Figma' conveys the purpose immediately. It earns its place, though the terseness borders on under-specification rather than deliberate brevity backed by richer content elsewhere.

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

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

With no annotations and no output schema, the one-sentence description must carry all context, but it omits what the tool returns, whether changes are undoable, and how resizing affects constraints or auto-layout parents. An agent calling this tool would have to guess at side effects and expected confirmation behavior, which is inadequate even for a simple 3-parameter mutation.

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 already documents all three parameters with clear descriptions ('New width', 'New height', 'The ID of the node to resize'). The description adds no additional parameter meaning beyond what the schema provides, so the baseline score of 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?

The description states a specific verb (resize) and resource (a node in Figma), making the core action unambiguous. It distinguishes from sibling tools because move_node, rename_node, delete_node, and clone_node each carry different verbs, so there is no overlap in what this tool does. It stops short of a 5 because it adds no scope detail (e.g., which node types are resizable) or explicit differentiation language.

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 guidance on when to use this tool versus alternatives such as move_node, set_layout_sizing, or set_layout_mode. There are no conditions, exclusions, or references to siblings, leaving the agent to infer appropriateness entirely 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?

No annotations provided, so description carries full burden. It discloses that locked nodes can be rotated (notable bypass of UI lock). However, it does not mention rotation center, anchor point, or impact on children, leaving some 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 concise with two sentences plus a note, no redundant information. Key details are front-loaded and 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?

For a simple rotation tool, the description covers primary behavior and a critical caveat. It lacks mention of rotation center but is otherwise sufficient given no output schema needed.

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 baseline is 3. Description adds value by specifying clockwise direction and clarifying the default behavior of relative (false) and the ability to rotate locked nodes, which are not in schema descriptions.

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

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

The description clearly states the verb (rotate), resource (node in Figma), and specific details (angle in degrees clockwise). It distinguishes from sibling transformation tools like move_node or resize_node by focusing on rotation.

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 the relative parameter and locked node behavior but does not explicitly state when to use this tool over alternatives like boolean_operation or apply_image_transform. Usage context is implied but not compared to 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 present, so the description carries the full burden of behavioral disclosure. It implies a read-only scan but does not explain whether the scan recurses through all descendants, what data is returned, or how results are formatted. 'Scan' alone is too vague for an agent to predict behavior reliably.

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 filler. It conveys the essential action and object efficiently, though it could include more behavioral detail without becoming bloated.

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 there is no output schema and no annotations, the description should explain what the tool returns or how the scan behaves. It does not mention return values, traversal depth, or any side effects, leaving significant ambiguity for a tool that an agent needs 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%, with nodeId described as 'ID of the node to scan.' The description adds only the phrase 'selected Figma node,' which maps loosely to the parameter but provides no extra semantic value. Baseline 3 is appropriate since the schema already documents the parameter.

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

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

The description states a specific verb ('scan') and a clear resource ('all text nodes in the selected Figma node'), so an agent can understand the core function. It does not explicitly differentiate from the sibling scan_nodes_by_types, but the focus on text nodes makes the purpose reasonably distinct.

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 about when to use this tool instead of alternatives like scan_nodes_by_types or get_node_info. The context of when this tool is appropriate is left entirely 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?

No annotations are provided, so the description carries the full burden. It discloses the write nature (adds) and the prerequisite, but does not detail whether the operation is idempotent, what happens if annotation already exists, 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 two sentences long, front-loads the main purpose, and every word adds value. There is no unnecessary 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?

Given the tool's simplicity (two required parameters, no output schema), the description is fairly complete. It covers the basic usage and prerequisite. However, it could benefit from a brief note about the return value or behavior when annotation already exists.

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 input schema already documents both parameters adequately. The description adds no extra meaning beyond the schema, meeting the baseline.

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

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

The description clearly states it adds an annotation label to a node in Figma, using a specific verb and resource. It distinguishes from the sibling tool 'get_annotation' which retrieves annotations.

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 specifies the prerequisite (Figma Desktop with enableProposedApi), providing clear context. However, it does not explicitly state when not to use this tool or mention alternatives beyond the implied contrast with 'get_annotation'.

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