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

Annotations already declare readOnlyHint=true, so the description's 'handshake ping' adds mild behavioral context (non-destructive). However, it does not discuss rate limits or failure modes.

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 efficiently conveys the tool's essence without extraneous information.

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

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

For a simple ping tool with an output schema, the description is too sparse. It fails to mention what the output indicates (success/failure) or error handling, 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 description coverage is 0%, and the description provides no explanation of the 'pid' parameter. The agent cannot infer what the integer represents or how to use 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?

The description clearly states it is a 'handshake ping' to verify plugin listener responsiveness, which is a specific and distinct purpose. It distinguishes from sibling tools that perform other functions.

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

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

No guidance on when to use this tool or when not to. Lacks mention of prerequisites or alternatives, leaving the agent without usage 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?

The annotations include destructiveHint: true, but the description adds no context beyond 'toggles visibility'. It fails to explain what the destructive nature refers to (e.g., state reset, data loss) or any side effects, leaving the agent without critical behavioral insight.

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 at one sentence. While it lacks detail, it is front-loaded and direct, with no wasted words. However, it could be longer to add necessary context without sacrificing 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?

Given the tool has two required parameters and an output schema, the description is insufficient. It does not explain what the parameters mean (e.g., pid identifier, is_available toggles to true/false), nor does it describe the return value. The destructive hint is not addressed, making the overall completeness low.

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

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

The input schema has 0% description coverage for its two required parameters (pid, is_available). The description provides no additional meaning or constraints for these parameters, leaving their purpose ambiguous.

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 'toggles' and identifies the resource 'visibility of the PyNet log/output window'. It clearly distinguishes the tool's function from sibling tools like get_output_window_status, which likely reads the status without modifying it.

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

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

No guidance is provided on when to use this tool versus alternatives such as get_output_window_status. The description does not mention prerequisites, context, 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 already provide destructiveHint. The description adds minimal behavioral context beyond 'creates', such as effects on existing modules or permissions 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?

A single sentence is concise but lacks necessary detail, achieving a middle ground.

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 only 1 sentence and no parameter info, the description is incomplete for a 2-parameter tool.

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

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

Schema description coverage is 0%, but the description does not explain the parameters (pid, name) at all, leaving the agent without semantic clues.

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 'Creates' and the resource 'new custom Tab (ButtonsModule) in the Ribbon', distinguishing it from siblings like delete_pynet_module.

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 or alternatives. 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?

The description adds 'permanently' to the existing destructiveHint annotation, emphasizing irreversibility but not disclosing other traits like required permissions or effects on dependencies. The annotation already signals destructiveness, so the description adds minimal new insight.

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 7-word sentence, very concise. However, it is too brief to inform the agent adequately, sacrificing substance for 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?

For a destructive tool with two required parameters, the description lacks important context such as error handling (e.g., if module doesn't exist), dependencies, and whether the deletion cascades. An output schema exists but does not compensate for missing 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 description does not explain the parameters 'pid' and 'module_id' beyond what is in the schema. With 0% schema description coverage, the tool relies entirely on the description for parameter meaning, which it fails to provide.

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

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

The description states the tool deletes a module and all its contents, clearly specifying the verb 'delete' and resource 'module'. However, it does not differentiate from sibling tools like 'delete_script_button', which also delete but on 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?

No guidance is provided on when to use this tool versus alternatives, such as the sibling tools that also perform deletions. There is no mention of prerequisites or conditions.

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

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

The annotation already provides 'destructiveHint: true', which signals destructiveness. The description adds 'permanently removes', consistent with the annotation. However, it does not disclose additional behavioral details like required permissions, cascading effects on other data, or error conditions. The annotation carries most of the burden here.

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 superfluous words. It is front-loaded with the action and resource. Every word 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?

Given the tool has three required parameters with no descriptions and a destructive action, the description should provide more context about the removal process, return value, or prerequisites. The output schema is present but its content is unknown; the description does not compensate for the lack of parameter documentation.

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

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

The input schema has 0% description coverage on parameters, and the description only says 'by Id', failing to explain what each parameter represents (e.g., pid likely a project ID, module_id a module, button_id the button identifier). The field names offer some clue but are insufficient for an agent to correctly map parameters without additional context.

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

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

The description clearly states that the tool 'permanently removes a ScriptButton from a module by Id'. It uses a specific verb ('removes'), identifies the resource ('ScriptButton'), and specifies the scope ('from a module by Id'). This distinguishes it from siblings like 'deploy_script_button' (create) and 'update_script_button' (modify).

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

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

The description provides no explicit guidance on when to use this tool versus alternatives like 'deploy_script_button' or 'update_script_button'. It does not mention prerequisites, when not to use, or how it fits into a workflow. The word 'permanently' hints at irreversibility but is not a substitute for explicit guidelines.

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 mark destructiveHint=true, but description doesn't disclose what makes it destructive (e.g., overwriting existing buttons). No contradiction, but missing 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?

Single sentence with 10 words, no fluff. Clearly states 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?

With 6 parameters, a destructive hint, and an output schema, the description is too sparse. Does not explain critical parameters like pid and module_id, nor return behavior.

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

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

Schema description coverage is 0%, but description lists Name, Script, Icon, Tooltip which helps map to parameters. However, pid and module_id remain unexplained.

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 'Installs' with clear resource 'ScriptButton into a specific module', and mentions parameters in parentheses. Distinct from sibling tools like update_script_button.

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 like update_script_button or delete_script_button. Doesn't 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?

Annotations already declare readOnlyHint=true, so the description adds little beyond that. It mentions the tool lists buttons by module ID, which is consistent but not additional 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?

Single sentence, concise and front-loaded. 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?

Description is minimal given two parameters without explanation. Output schema exists but is not shown; return values may be documented there. However, more context about the purpose of pid would improve completeness.

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

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

Schema coverage is 0%; description does not explain the parameters pid or module_id beyond implying module_id is the module ID. With low coverage, the description fails to add meaning to the parameters.

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

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

Description clearly states verb 'Lists' and resource 'script buttons' with a qualifier 'for a specific module ID'. It is specific and distinguishes from sibling tools like delete_script_button or deploy_script_button.

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. However, the read-only nature is implied by the description and annotations, distinguishing it from mutation tools among siblings.

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

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

Annotations already declare readOnlyHint=true. Description adds minimal context about checking availability/visibility, but does not specify return format or edge cases. Adequate but not comprehensive.

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. 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?

For a simple tool with a single parameter and an output schema, the description is minimal but acceptable. However, the lack of parameter explanation and return value context leaves room for improvement.

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

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

Schema coverage is 0% with no parameter descriptions. The description does not mention the 'pid' parameter, leaving the agent without any context on what value to provide.

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

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

The description clearly states the verb 'checks' and the resource 'output window status' with specific scope 'available/visible'. It uniquely distinguishes this tool from sibling tools like viewer_status or check_plugin_status.

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. No mention of prerequisites or context. Usage context is implied from the tool name alone.

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

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

Annotations provide readOnlyHint=true, so the tool is safe. The description adds context about the fetched content (ButtonsModules and ScriptButtons). It does not disclose potential errors, performance implications, or authorization needs, but annotations cover the safety aspect.

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, 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?

While the output schema exists, the description omits explanation of the required 'pid' parameter. It also lacks comparison with sibling tools. For a tool with one required parameter, this is insufficient.

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

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

Schema description coverage is 0%, and the description does not explain the 'pid' parameter. The agent has no information about what 'pid' represents or how to use 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?

The description clearly states the tool fetches the full UI structure (ButtonsModules and ScriptButtons). The verb 'Fetches' and resource are specific, but it does not explicitly differentiate from sibling tools like 'get_buttons_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 guidance is provided on when to use this tool versus alternatives. The description implies it is for obtaining the full UI layout, but does not mention exclusions or context (e.g., compare with get_buttons_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?

Annotations already provide readOnlyHint=true, and description adds behavioral context by specifying the condition of an active PyNet IPC pipe, which is valuable beyond the annotation. 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?

Single sentence, front-loaded with action, no unnecessary words. Highly 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 zero parameters and an existing output schema, the description fully explains the tool's purpose and behavior. It is complete for an agent to invoke without additional 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?

No parameters exist, so schema coverage is 100%. The description adds meaning by defining the scope of scanning (processes with active pipe), which compensates for the absence of parameters.

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

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

Description clearly specifies the verb 'scans' and the resource 'running Autodesk processes with an active PyNet IPC pipe', distinguishing it from sibling tools which focus on plugin, UI, or viewer operations.

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 sibling tools are different, the description implies its usage for discovering active instances, but no when-not-to or prerequisites are stated.

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

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

Annotations already mark destructiveHint=true; description adds 'direct script execution' but lacks details on side effects or permissions beyond annotation.

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 parenthetical list; efficient but could better structure parameter explanation.

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?

Destructive tool with 4 required params and no schema descriptions; description lacks scripting constraints, output explanation, and usage context despite having an output schema.

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

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

With 0% schema coverage, description mentions pid, script_name, content but omits timeout and offers no format/type guidance for content or script_name.

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 'execute' and resource 'script' with key parameters (PID, Script Name, Content), distinguishing from sibling send_command_by_path which uses path instead of PID.

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

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

Implies usage for direct script execution by PID but provides no explicit conditions or comparison with alternative send_command_by_path.

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?

Description aligns with annotations (destructiveHint=true) and adds the behavioral distinction of executing via path vs inline. However, it does not disclose other traits like authentication needs, rate limits, or side effects beyond execution.

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 that is front-loaded and efficient, 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?

Despite having an output schema (not shown), the description omits critical context for a destructive, path-based execution tool: file existence, permissions, error handling, and typical usage scenarios. This is inadequate given the tool's complexity.

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

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

Schema has 0% description coverage, and the description provides no meaning for any of the 4 required parameters (pid, script_name, file_path, timeout). The agent must infer solely from parameter names, which is insufficient for correct invocation.

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 ('Executes a script file directly by path') and the resource ('in the PyNet engine'), and contrasts with inline sending, distinguishing it from sibling tool 'send_command'.

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?

Implied usage when a script file path is available, but no explicit guidance on when to use this tool versus alternatives like send_command, 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?

The annotations already declare destructiveHint=true, and the description confirms mutation by using 'updates' and 'moves'. However, no additional behavioral details are given (e.g., authorization requirements, side effects, or rollback capabilities), so the description adds limited value beyond the annotation.

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

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

The description is a single sentence that efficiently communicates the two core functions upfront. There is no redundant information, and 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?

Despite having 8 parameters (7 required) and an output schema, the description does not clarify parameter groupings, the optional nature of dest_module_id for moving, or what the output contains. An agent would need additional context to use the tool correctly.

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

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

With 0% schema description coverage, the description should compensate but only weakly connects 'metadata' to parameters like name, tooltip, and icon_name, and 'move' to dest_module_id. It does not explain the role of each parameter or provide examples, leaving the agent to infer the mapping.

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 two specific actions (updating metadata and moving to another module) with a concrete resource (ScriptButton). It effectively distinguishes from sibling tools like delete_script_button and deploy_script_button by specifying the operations that are unique to this tool.

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

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

The description implies usage for updating or moving a ScriptButton, but it does not explicitly state when to use this tool versus alternatives such as delete_script_button or deploy_script_button. No exclusions or context-specific 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?

Annotations declare readOnlyHint: true, but the operation modifies the viewer's visual state. The description does not elaborate on side effects or whether the action is reversible. However, it is clear that it removes existing highlights/ghosting.

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, informative sentence with no unnecessary words. It front-loads the core action and object.

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

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

For a simple tool with no parameters and an output schema, the description is sufficient. It could be improved by noting that it affects only the open viewer.

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 no parameters, so the baseline is 4. The description does not need to add parameter details since the schema is empty and 100% covered.

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

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

The description clearly states the specific action ('clears') and the target resource ('highlights and ghosting in the open viewer'). It distinguishes from sibling tools like viewer_highlight_clash and viewer_isolate.

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 it should be used after highlights or ghosting are applied, but does not mention 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?

Annotations already indicate readOnlyHint=true, so the read-only safety is covered. The description adds value by specifying that the camera fits to 'all models' (not just selected), which is a behavioral trait. 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 a single sentence that is perfectly front-loaded and contains no fluff. Every word 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?

Given the tool has no parameters, simple action, and an output schema (mentioned in context), the description is complete. An agent can understand exactly what the tool does without additional 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?

There are zero parameters, and schema coverage is 100% trivially. The description does not need to add parameter details. Baseline 4 is appropriate for no parameters.

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

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

The description clearly states the action ('fits the camera') and the target ('all models in the open viewer'), distinguishing it from sibling tools like 'viewer_isolate' or 'viewer_clear'. The verb 'fits' is slightly technical but specific enough for an AI agent.

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 like 'viewer_isolate' or 'viewer_select'. It lacks context for prerequisites or situations where this tool is 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?

Annotations already provide readOnlyHint. Description adds valuable context: the data comes from properties.json, not the viewer; the tool returns an index when called without pnt_ids. No contradictions with annotations.

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

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

Two short paragraphs, front-loaded with the core purpose. Every sentence adds value; no wasted words. Highly 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 presence of an output schema, description need not detail return structure. It covers dual behavior and data source. Could mention error handling or prerequisites, but for a read-only tool with one optional param, it is sufficiently complete.

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

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

Schema coverage is 0%, so description fully explains the single parameter pnt_ids: optional, triggers property retrieval when provided, or returns a lightweight index when omitted. This meaningfully compensates for the lack of schema description.

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

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

Description clearly states it reads element properties from properties.json, with specific verb 'reads' and resource 'element properties (name, model, psets)'. Distinguishes from siblings by specifying the data source and dual behavior (index vs. full properties).

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

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

Explicitly says when to use with pnt_ids and without, and clarifies the data source is NOT the viewer or IFC. No explicit when-not or alternatives to sibling tools, but the context is clear enough for selection.

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

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

The description aligns with the readOnlyHint annotation, confirming a read-only operation. It adds useful detail about the return value ('list of loaded models'), which is beyond what the annotation provides, enhancing 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, clear sentence with no unnecessary words. It front-loads the action and outcome efficiently.

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

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

For a simple, parameterless tool with an output schema, the description is complete. It indicates what is returned (the state, currently list of models) and the read-only nature, covering all essential aspects.

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

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

There are no parameters, so per guidelines the baseline is 4. The description does not need to add parameter information and is adequate for a parameterless tool.

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

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

The description clearly states the tool reads the viewer's last reported state and specifies it currently returns the list of loaded models. It uses a specific verb ('Reads') and resource ('viewer's state'), and distinguishes from sibling viewer tools like viewer_get_properties or viewer_isolate by focusing on general state.

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?

Although no explicit when-to-use or when-not-to-use instructions are given, the tool has no parameters and the purpose is straightforward. Given the sibling tools, it's clear this is the generic state reader, so 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?

Annotation indicates destructiveHint=true, but the description describes a non-destructive highlight operation. This contradiction undermines transparency. No other behavioral traits are disclosed.

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 efficient sentence, front-loaded with the action. No unnecessary words, though the parenthetical could be clearer regarding the color mapping.

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 that annotations provide destructiveHint=true (contradicting) and no output description, the tool lacks essential context. It doesn't mention that the viewer must be open, what happens if pnt_ids are invalid, or the return value (output schema exists but unused). 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 has 0% description coverage. The description adds mapping: pnt_id_a for element A (red), pnt_id_b for element B (green), which provides some meaning beyond the schema. However, it lacks details on valid values, format, or optionality.

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 'highlights', the resource 'clash pair', and specifies the visual effect (element A red, element B green). It distinguishes well from sibling tools like viewer_isolate or viewer_select.

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, nor any prerequisites mentioned. The description does not address when highlighting is appropriate compared to viewer_isolate or other 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?

The description adds important behavioral context beyond annotations: it notes that the command is broadcast but currently ignored due to a pending frontend handler. This alerts the agent to a potential no-op. The destructiveHint annotation is consistent with the description.

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

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

Two sentences: first states the core function, second adds critical behavioral disclosure. 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?

The description covers purpose, parameter meaning, and current limitation. It assumes the viewer is open (implied by 'in the open viewer'). With an output schema present but not described, the description is sufficient for a simple 1-parameter 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 'pnt_ids' has 0% schema description coverage, so the description must compensate. It explains that these are the IDs to isolate to, but lacks detail on format or constraints. The parameter is not required, but no default behavior is described.

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: 'Isolates (hides everything except) the given pnt_ids in the open viewer.' It uses a specific verb 'isolates' and specifies the resource 'viewer'. This distinguishes it from sibling tools like viewer_clear or viewer_select.

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 (to hide all except given point IDs) but does not provide explicit guidance on alternatives or when not to use. No comparison with sibling tools is given.

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

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

Annotations declare readOnlyHint=true; description adds context that it reads a specific file (clashes.json) rather than viewer data. No contradictions. Clarifies the non-destructive nature and data source.

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 covering purpose, data source, and key output. No extraneous content.

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

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

Given zero parameters, presence of output schema, and simple read-only operation, the description provides sufficient context. It mentions the critical return element (pnt_id identifiers) that aids tool selection.

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 (schema coverage 100%). Description adds meaning by specifying that the return includes pnt_id identifiers for highlighting, which is useful beyond the empty schema.

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

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

Clearly states it reads clashes.json (data source) and returns clash data with pnt_id identifiers for highlighting. Distinguishes from viewer/IFC and sibling tools like viewer_highlight_clash.

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?

Explains the tool's input (loaded package's clashes.json) and output (pnt_id identifiers). Implicitly contrasts with viewer/IFC and highlighting tool, but does not explicitly state when not to use alternatives.

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

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

Annotations already indicate destructive hint, so description should elaborate on side effects. It mentions loading but does not clarify if previous viewer state is cleared, overwritten, or merged. The return of a summary is noted but not the behavioral impact on viewer state.

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

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

Single sentence, efficient, front-loaded with action and result. 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?

Given the destructive hint and a single parameter, the description lacks completeness. It does not state if viewer must be empty, if loading fails gracefully, or how the summary is used. Output schema is present but not described.

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

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

Schema coverage is 0%, so description must add meaning. It mentions 'pnt_path' implicitly but provides no details on file format, required permissions, or format constraints. The parameter is not explained beyond its name.

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 ('loads'), the resource ('.pnt file'), the destination ('open viewer'), and the return value ('summary from clashes.json'). It is specific and distinguishes from sibling tools like viewer_clear or viewer_highlight_clash.

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

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

No guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., viewer must be open) or typical workflow (e.g., use after viewer_list_clashes).

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?

Description notes that the tool replaces any previous selection, aligning with destructiveHint: true. Adds color distinction for second group. No contradiction with annotations.

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

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

Three sentences, front-loaded with primary function. Could be slightly more concise, but no waste.

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

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

Covers key behaviors: highlighting, replacement, and obtaining IDs. Lacks details on error handling or behavior with invalid IDs. Output schema exists, so return value is not 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 0%, so description compensates partially. Explains pnt_ids as group A and pnt_ids_b as optional second group with distinct color, but does not detail array format or behavior when both are empty.

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

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

The description clearly states the action ('highlights'), the resource ('elements in the open viewer'), and the identifier ('by pnt_id'). It distinguishes from sibling tools like viewer_clear and viewer_isolate by focusing on highlighting.

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 says to use viewer_list_clashes or viewer_get_properties to obtain pnt_ids, and describes optional second group. Lacks explicit when-not-to-use, but overall context is clear.

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

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

Annotations already declare readOnlyHint=true, so the description adds value by specifying the reported status info. No contradictions exist, but the description does not elaborate on other behavioral traits like authentication or permissions.

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, well-structured sentence that conveys the core purpose and output immediately. 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?

Given the absence of parameters, the presence of readOnlyHint annotation, and an output schema, the description sufficiently explains what the tool does. It lacks only minor context like error conditions or response format, but the output schema covers that.

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 description does not need to explain parameter semantics. The baseline score 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 tool's purpose: reports whether a PyNet BIM Viewer is open in VS Code, and specifies the details it provides (port, package, data dir). While it differentiates from siblings by focusing on the viewer status, it does not explicitly exclude other status-checking 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 such as check_plugin_status or list_active_instances. Agents must rely on the tool name and context to infer usage.

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