Server Quality Checklist

Tool Scores

• tc_systemD
  1.7/5.0
  Behavior2/5

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

  With no annotations, the description must fully disclose behavioral traits. It fails to indicate anything about side effects (e.g., set_netid is a write, rescan_plc may disrupt bus), permissions needed, error behavior, or synchronous vs asynchronous execution. The description is insufficient for safe invocation.

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

  Conciseness2/5

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

  The description is a single line that crams multiple actions with parenthetical notes without clear structure. It is underspecified and cryptic, wasting the opportunity to inform. Conciseness should serve clarity, not replace it.

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

  Completeness1/5

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

  Given the tool has 3 parameters, 0% schema description coverage, no output schema, and no annotations, the description is severely incomplete. It does not explain return values, error handling, or which parameters are required per action. It fails to meet even minimal completeness for a multi-action system tool.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate. It mentions 'path' and 'netId' but does not explain their types, formats, or which actions require them. The action enum values are listed inline, but 'errors' and 'scan_io_boxes' are described in a confusing way (e.g., 'IO device node' is unclear). The description adds minimal clarity beyond the schema.

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

  Purpose2/5

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

  The description attempts to list multiple actions but does so in a fragmented, ambiguous way. It reads as a mix of subcommands and notes (e.g., 'netId', 'errors (latest messages)') without a clear overall statement that this tool dispatches system management operations based on the 'action' parameter. The purpose is unclear and requires inference.

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

  Usage Guidelines1/5

  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 siblings like 'tc_ethercat' or 'tc_link'. There is no explanation of prerequisites, context, or what each action is typically used for. The agent is left to guess usage cases.

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

• xae_buildC
  2.6/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits. It only mentions that the tool waits for completion by default. It does not explain what happens on build failure, whether the tool is destructive, what output is returned, or any side effects like project file modification. Critical information is missing.

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

  Conciseness3/5

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

  The description is a single sentence, which is concise but lacks structure. It front-loads the main action but omits any secondary details. While not verbose, it is too terse to be considered well-structured for a tool with three parameters.

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

  Completeness2/5

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

  Given the tool has three parameters, no output schema, and no annotations, the description is incomplete. It does not explain the build process, error handling, or how this tool fits into the broader TwinCAT ecosystem. The sibling tools suggest a rich context, but the description fails to leverage or clarify it.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description should compensate. It only hints at the waitForFinish parameter (default wait). The action enum values are self-explanatory, but the timeoutMs parameter is entirely unexplained. The description adds minimal meaning beyond the schema.

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

  Purpose4/5

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

  The description clearly states the tool performs clean/build/rebuild actions on the active solution configuration, which is a specific verb-resource combination. However, it does not explicitly differentiate from sibling tools like xae or xae_command, and the phrase 'active solution configuration' may assume domain knowledge.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives. It does not specify prerequisites, when to choose clean vs build vs rebuild, or any conditions that would make this tool inappropriate. This is a significant gap.

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

• ncC
  2.8/5.0
  Behavior2/5

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

  With no annotations, the description must disclose behavioral traits. It indicates 'returns info + children' for axis, but does not confirm read-only behavior, mention side effects, error conditions, or required permissions. The terse style leaves significant ambiguity.

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

  Conciseness3/5

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

  The description is extremely concise (one line) but uses cryptic phrasing and no structural elements like bullet points or separate sections. This sacrifices immediate clarity for brevity.

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

  Completeness2/5

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

  Given no output schema and limited parameter descriptions, the description does not adequately cover behavior, return values, or error handling. For a tool with only 2 parameters and a single enum, it still leaves key details unspecified (e.g., default behavior for path in 'tasks').

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

  Parameters3/5

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

  Description adds meaning to the action enum (tasks, axes, axis) and hints at path usage (e.g., 'path = task' for axes, 'path = full axis path' for axis). However, 0% schema coverage means it must fully compensate; the path parameter usage remains underspecified (e.g., optional vs required per action, format).

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

  Purpose4/5

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

  The description clearly identifies the tool as querying the 'NC motion tree' and lists three distinct actions (tasks, axes, axis) with brief explanations of each. This differentiates it from sibling tools that focus on PLC, EtherCAT, or system configuration.

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

  Usage Guidelines2/5

  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., tc_mapping, tc_task). The description only enumerates actions without stating prerequisites, limitations, or recommended scenarios.

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

• plc_downloadB
  3/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden. It discloses the autoLogout behavior (logs out via UI Automation if needed and never logs back in) and method differences. However, it does not mention failure scenarios, overwrite behavior, or whether the runtime is restarted after deployment.

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

  Conciseness3/5

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

  The description is a single block of text that front-loads the main purpose. It contains useful details without excessive verbosity, but lacks structure (e.g., bullet points for parameters) and could be more scannable for an agent.

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

  Completeness2/5

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

  Given 6 parameters, no output schema, and sibling tools like twincat_restart_runtime, the description should cover deployment nuances. It addresses methods and logout but omits autostart default behavior, commandName usage, treePath selection, and return value expectations. This leaves significant gaps for an agent.

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

  Parameters2/5

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

  Schema coverage is only 17% (only treePath described). The description adds meaning for method, confirm, and autoLogout but ignores autostart, commandName, and treePath details. Even confirm is only implied as required. This is insufficient for a 6-parameter tool with low schema coverage.

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

  Purpose4/5

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

  The description clearly states the tool deploys the active PLC project, using specific verbs like 'deploy' and 'writes to target boot dir'. It distinguishes the two methods (bootproject and command) but does not explicitly differentiate from sibling tools like xae_build or twincat_restart_runtime.

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

  Usage Guidelines3/5

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

  The description provides guidance on when to use each method (headless vs. needing window automation) and the required confirmation token (confirm=

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

• xae_commandB
  3.2/5.0
  Behavior3/5

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

  No annotations are provided, so the full burden falls on the description. It discloses one behavioral aspect: the guarded execution requiring a specific confirmation string. This hints at potential destructive or sensitive operations. However, it does not mention whether the command modifies state, has side effects, or what errors may occur. Partial disclosure but insufficient for full transparency.

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

  Conciseness4/5

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

  The description is very concise: two sentences with no filler. It front-loads the action and quickly gives context (guard). However, it could be slightly restructured for readability, e.g., separating the guard condition more clearly. Overall, it is appropriately sized for a short description.

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

  Completeness3/5

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

  Given that the tool has 3 parameters, 0% schema coverage, and no output schema, the description is minimally complete: it covers the main action and a critical constraint (guard). However, it omits details about parameter syntax (e.g., format of args), return behavior, and error cases, which are important for safe invocation. The complexity is moderate but the coverage gap means more description is needed.

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

  Parameters2/5

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

  Schema description coverage is 0%, meaning the schema provides no descriptions for the three parameters. The description only mentions "commandName" implicitly via the example "View.SolutionExplorer" and the guard "confirm" as the required string. No semantics for "args" parameter are given. Since the description must compensate for the lack of schema documentation but only partially does, the score is low.

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

  Purpose4/5

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

  The description clearly states the action: "Execute a raw XAE/DTE command by name", giving a specific verb (Execute) and resource (XAE/DTE command). It also provides a concrete example (View.SolutionExplorer), which helps distinguish it from sibling tools like tc_system or plc_download. However, it slightly lacks a fuller scope statement (e.g., what commands are valid or what environment it targets).

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

  Usage Guidelines3/5

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

  The description mentions a guard condition ("confirm=\"ALLOW_XAE_COMMAND_EXEC\""), which is a critical prerequisite for use. However, it does not explain when to use this tool versus alternatives (e.g., when to use tc_system instead) or what types of commands are appropriate. No explicit when-not-to-use guidance is provided, leaving ambiguity for an AI agent.

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

• twincat_activate_configurationB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of disclosing behavioral traits. The description only mentions that confirmation is required but does not reveal side effects (e.g., whether activation restarts the runtime, disrupts existing tasks, or requires specific permissions). Activating a configuration is typically a disruptive operation, and the lack of such disclosure makes the description inadequate for safe tool selection.

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

  Conciseness5/5

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

  The description is extremely concise at two sentences with no wasted words. It front-loads the purpose ('Activate the TwinCAT configuration on the target') and immediately follows with the essential guard condition. Every sentence earns its place, and no redundant information is present.

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

  Completeness2/5

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

  Given that this tool has a single parameter, no output schema, and no annotations, the description is insufficient for a complete understanding. It does not explain what happens after activation (e.g., return values, errors, or confirmation messages), nor does it clarify whether activation is reversible or requires a restart. For a potentially disruptive operation, more context is needed.

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

  Parameters3/5

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

  Schema description coverage is 0%, meaning the schema provides no descriptive text for the single parameter 'confirm'. However, the tool description explicitly explains that the parameter value must be 'ALLOW_TWINCAT_ACTIVATE', adding significant semantic meaning beyond the raw schema (which only defines type 'string'). This compensates for the schema's lack of documentation, earning a baseline 3. It does not reach 4 because the description does not explain what happens if the wrong string is provided.

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

  Purpose4/5

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

  The description clearly states the action ('Activate'), the resource ('TwinCAT configuration'), and the target ('on the target'), making the purpose unambiguous. It also mentions a guard mechanism ('confirm=ALLOW_TWINCAT_ACTIVATE'), which adds important context. However, it does not explicitly distinguish this tool from siblings like 'twincat_restart_runtime' or 'plc_download', leaving some ambiguity for agents deciding between activation and related operations.

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

  Usage Guidelines4/5

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

  The description provides explicit usage guidelines by stating that the tool is 'Guarded' and requires a specific confirmation string ('ALLOW_TWINCAT_ACTIVATE') as the parameter. This tells the agent when and how to use it (only with proper confirmation). However, it does not mention when not to use this tool (e.g., preferring 'plc_download' for code changes) or provide alternatives among the 25 sibling tools, so it falls short of excellence.

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

• xaeB
  3.4/5.0
  Behavior4/5

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

  With no annotations, the description discloses important behavior: open_solution's closeExisting/discardChanges semantics, error_list's default limit and filter-before-cap behavior, dialog_probe being read-only, and dialog_resolve's auto-remember refusal for destructive prompts. However, it remains silent on side effects for actions like save_all, clear_error_list, and list_commands.

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

  Conciseness3/5

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

  The description is a single dense paragraph that packs a lot of vital behavioral detail, but the lack of structure (e.g., bulleted actions) makes it hard to scan. Every clause earns its place, yet formatting could dramatically improve readability.

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

  Completeness3/5

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

  For a 10-parameter, multi-action tool with no output schema, the description thoroughly documents open_solution, error_list, dialog_probe, and dialog_resolve, but omits expected return values or side effects for status, save_all, active_document, selected_items, clear_error_list, and list_commands. This leaves significant gaps for the agent to infer.

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

  Parameters4/5

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

  The schema covers only 20% of parameters with descriptions; the text compensates by explaining solutionPath, closeExisting, discardChanges, limit, severityFilter, filter, button, and remember within the context of their actions. This embedded documentation adds practical meaning (e.g., severityFilter 'errors'|'warnings' with true total count) beyond the bare schema enum.

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

  Purpose4/5

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

  The description clearly identifies the tool as an 'XAE shell' command dispatcher, enumerating the distinct operations it supports (status, open_solution, error_list, dialog_probe, etc.). It differentiates from sibling tools by listing these shell-specific actions, though it lacks a single declarative sentence stating the tool's core purpose (e.g., 'Execute XAE shell commands').

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

  Usage Guidelines2/5

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

  The description provides use-case context for individual sub-actions (e.g., dialog_probe checks for a blocking modal, dialog_resolve clicks the chosen button), but it does not explain when to use this tool over specialized siblings like xae_build, tc_system, or plc_download. There is no explicit guidance on when not to use it or which alternative to pick for a given scenario.

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

• twincat_restart_runtimeA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries full transparency burden. It reveals the guarded nature ('confirm=ALLOW_TWINCAT_RESTART'), indicating a safety-conscious operation. However, it does not disclose side effects like stopping PLC programs, network interruptions, or state changes to the runtime system, leaving gaps in understanding the full impact.

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

  Conciseness5/5

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

  The description is extremely concise—two sentences covering purpose and guard condition. No redundant information; every word earns its place.

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

  Completeness3/5

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

  For a simple restart tool, the description covers purpose and guard but lacks details about prerequisites (e.g., runtime must be active), post-restart behavior, or return values. Since there is no output schema, the description could usefully indicate that the tool returns success/failure or triggers a reboot, but it does not. Still, the core functionality is adequately conveyed.

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

  Parameters4/5

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

  The schema only defines 'confirm' as a string with no description. The description adds critical meaning by specifying the exact required value 'ALLOW_TWINCAT_RESTART', which is essential for correct invocation. This compensates for the 0% schema description coverage.

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

  Purpose5/5

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

  The description clearly states the verb 'start/restart' and the resource 'TwinCAT runtime on the target', making the tool's purpose unambiguous. It also implicitly distinguishes from sibling tools like 'xae_build' or 'plc_download' which handle different operations.

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

  Usage Guidelines2/5

  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 'twincat_activate_configuration' or 'tc_system'. The description does not mention prerequisites, context of use, or scenarios where this tool is appropriate versus other runtime management tools.

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

• plc_libraryA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses that READ has no side effects, WRITE involves offline .plcproj edits with no runtime impact, and REPO ADMIN mutates machine-wide state. It also notes the LANDMINE about solution close/reopen and that repo admin is guarded with confirm. It does not cover error handling or concurrency, but the coverage is substantial.

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

  Conciseness4/5

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

  The description is long but well-structured with clear sections (READ, WRITE, LANDMINE, REPO ADMIN). It is front-loaded with the core purpose. Every sentence adds useful information, though it is dense and could be slightly trimmed without losing clarity.

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

  Completeness4/5

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

  Given the tool's complexity (20 parameters, many actions) and no output schema, the description covers the main actions, their effects, and key caveats. It provides partial output structure for READ actions (e.g., 'list → name/kind/displayName/...') but lacks details for WRITE and REPO ADMIN return values. Overall, it is fairly complete for an agent to understand usage.

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

  Parameters3/5

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

  Schema description coverage is only 15%, so the description must compensate. It explains the action enum values in detail, and for each action it lists relevant parameters (e.g., add_library takes name, version?, company?). However, several parameters (lib, dist, mode, index, confirm, etc.) are not explained or only partially covered. The description adds value but is not comprehensive.

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

  Purpose5/5

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

  The description clearly states the tool manages PLC library references, placeholders, and repositories via ITcPlcLibraryManager. It lists specific actions (list, scan, repos, add_library, etc.) and their effects. It distinguishes itself from sibling tools by focusing on library management, not build, download, or other TwinCAT operations.

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

  Usage Guidelines4/5

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

  The description provides explicit guidance on when to use each action, including READ vs WRITE distinctions, and the LANDMINE about needing solution close/reopen for certain edits. It also mentions the confirm parameter requirement for repo admin. However, it does not explicitly state when NOT to use this tool or compare to alternatives.

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

• tc_ethercatA
  4.2/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses behavioral traits: the native creation method, expansion from ESI, handling of ghost/unknown types (cleanup and ok:false), optional save, and the flat return format. It also explains the ordering and insertion behavior, leaving no ambiguity about 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.

  Conciseness3/5

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

  The description is a single dense paragraph that packs extensive technical detail. While front-loaded with the main purpose, it lacks breaks or sections to aid scanning. Every sentence is substantive, but the length makes it less concise than ideal for quick agent comprehension.

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

  Completeness5/5

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

  Given the tool's complexity (nested parameters, no output schema, no annotations), the description covers all necessary aspects: purpose, input structure, behavior on failure, revision pinning, ordering, and the complete return format. No critical gaps remain for an agent to invoke the tool correctly.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description must explain all parameters. It does so thoroughly: the racks array structure, parent, modules with type, name, before, and revision. It explains the meaning of 'type' as a plain product string, the 'before' insertion semantics, and the complex revision pinning format with examples. This goes far beyond the bare schema.

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

  Purpose5/5

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

  The description begins with 'Create EtherCAT IO boxes (terminals/couplers) NATIVELY,' clearly stating the specific verb and resource. It distinguishes from sibling tools like tc_fieldbus or tc_module by focusing exclusively on EtherCAT terminal creation with a unique native method, which is not mentioned elsewhere.

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

  Usage Guidelines2/5

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

  The description provides detailed usage instructions for the tool itself (e.g., parameter format, revision pinning, error handling) but does not advise when to use this tool over alternatives like tc_fieldbus or tc_module. No explicit 'when-not-to-use' or comparison to siblings is included.

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

• tc_linkA
  4.2/5.0
  Behavior3/5

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

  No annotations exist, so the description must fully disclose behavior. It covers some aspects: mutation with save:true, read-only 'resolve' and 'links' actions, default roll-up for batches, and compact output. However, it omits permission requirements, idempotency, side effects, and error handling details. The transparency is adequate but incomplete.

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

  Conciseness3/5

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

  The description is a single dense paragraph that contains all necessary information but lacks bullet points, section headers, or clear organization. Front-loading is present first sentence states purpose but the text becomes overwhelming with technical specifics, making it less efficient for an AI agent to parse.

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

  Completeness4/5

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

  For a tool with 8 parameters and no output schema, the description covers the main use cases, parameter interactions, and optimization advice (batch-first). It explains resolve return format and links action behavior. However, it does not specify return values for link/unlink actions and leaves the autoResolve parameter unexplained. The description is mostly complete for basic operations.

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

  Parameters4/5

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

  Schema description coverage is only 25%, but the description compensates by attributing meanings to most parameters: a=source, b=destination, links=[{a,b}], action enum, details for full rows, verbose for resolution detail. The autoResolve parameter is not explicitly described, and some parameter behavior (optional b for unlink) is only implicitly stated. Overall, the description adds significant value beyond the schema.

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

  Purpose5/5

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

  The description explicitly states that the tool manages variable links (producer↔consumer) and provides a clear list of actions (link, unlink, resolve, links, and batch variants). It distinguishes the batch versions as BATCH-FIRST for multiple links, making the core purpose unambiguous despite technical jargon.

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

  Usage Guidelines5/5

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

  The description gives explicit guidance on when to use batch verbs ('for more than one link use link_batch/unlink_batch') and explains default behaviors (failures-only roll-up, compact vs verbose output). It also clarifies optional flags (details, verbose, save) across actions, providing context for selecting the right approach.

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

• tc_cppA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description fully discloses behavior: build does not deploy, publish does not activate/restart runtime, ConsumeXml wrapper element details, and fallback logic. The caveat about ProduceXml to confirm element names adds important nuance. A slightly more organized summary would improve clarity, but transparency is strong.

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

  Conciseness3/5

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

  The description is dense at over 500 words, covering seven actions and many details. While every sentence adds value, the structure is a single paragraph block with inline action descriptions and a trailing caveat. Better formatting (e.g., bullet lists or subheadings) would improve scannability for an AI agent.

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

  Completeness4/5

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

  Given the tool's complexity (14 parameters, 7 actions, no output schema, no annotations, many siblings), the description covers most aspects: each action's purpose, parameter usage, fallbacks, and limitations. It addresses potential pitfalls (e.g., ConsumeXml element names). Missing explicit return value or error handling information, but the overall completeness is high.

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

  Parameters5/5

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

  Schema description coverage is only 7% (only 'before' has a brief description). The description compensates thoroughly: it explains each action's parameters in context (e.g., template enum values and fallback, subType meanings, confirm guard for publish, default config and timeoutMs). This adds significant meaning beyond the sparse schema.

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

  Purpose5/5

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

  The description clearly states the tool is for TwinCAT C++ projects/modules under TIXC, explicitly listing seven distinct actions. It distinguishes from siblings by stating 'C++ ONLY — TISC (safety) untouched' and noting runtime needs a later activate/download, which sets it apart from activation tools like twincat_activate_configuration.

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

  Usage Guidelines4/5

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

  The description provides explicit context: 'C++ ONLY — TISC (safety) untouched' tells when not to use for safety projects. It details action-specific usage (e.g., template fallback, subType options, guarded publish). However, it does not explicitly list alternative tools for specific scenarios, relying on the sibling list for comparison.

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

• tc_mappingA
  4.3/5.0
  Behavior5/5

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

  With no annotations, the description carries full burden and excels: discloses read-only nature of produce, mutation scope of consume, destructive guarded nature of clear, that operations affect offline config only, and safety implications for TwinSAFE links. It also notes the XML schema is undocumented, setting proper expectations.

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

  Conciseness4/5

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

  The description is detailed but not overly verbose; it front-loads the purpose and method, then explains each action, safety, and notes. Some redundancy exists (repeating 'PROJECT-WIDE', 'NOT runtime writes'), but overall each sentence adds value given the complexity of the tool.

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

  Completeness5/5

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

  For a tool with 4 parameters, no output schema, and no annotations, the description covers all essential aspects: operation semantics, parameter roles, safety precautions, scope, and even advises on handling the unknown XML schema. The return value of produce is explicitly stated. No gaps remain for an agent to operate correctly.

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

  Parameters4/5

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

  Schema coverage is 0%, so description must explain parameters. It does so by associating 'xml' with produce output and consume input, 'save' as optional for consume/clear, 'action' enum fully explained, and 'confirm' required for clear. While not a structured parameter list, it effectively conveys usage context. Minor improvement would be explicit mapping of each parameter to its operation.

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

  Purpose4/5

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

  The description clearly states it handles bulk variable-mapping operations (produce, consume, clear) on the entire TwinCAT project, not individual links. It mentions being whole-project and not tree-path specific. However, it does not explicitly differentiate from sibling tool 'tc_link', which likely handles individual link operations, leaving some ambiguity for the agent.

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

  Usage Guidelines4/5

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

  The description provides detailed context for each operation: produce is read-only, consume mutates offline config, clear is destructive with a required confirmation token. It advises running produce first as a backup and warns about TwinSAFE involvement. However, it lacks explicit guidance on when to use this tool versus sibling tools like tc_link for individual mappings.

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

• tc_taskA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses key behavioral traits: config-only, no confirm token needed, runtime activation needed later, TISC untouched, caveat about unconfirmed tag names, unit conversions (cycleTimeUs to 100ns ticks), and mutual exclusion of typed fields vs xml escape hatch. However, it does not cover authorization needs or error handling, which prevents a perfect score.

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

  Conciseness4/5

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

  The description is a single dense paragraph that front-loads the main purpose and then lists actions with their parameter details. Every sentence provides essential information, but it could be better structured (e.g., bullet points or sections) to improve readability without losing content. Still, it is appropriately concise for the complexity.

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

  Completeness5/5

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

  Given the tool has 19 parameters, 10 actions, no output schema, and no annotations, the description is remarkably complete. It covers all actions, parameter semantics, special behaviors (e.g., ConsumeXml, unit conversions, caveats), and structural context (tree paths with ^ separators). The only minor gap is lack of error handling or return value description, but the absence of an output schema makes this acceptable.

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

  Parameters5/5

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

  The schema description coverage is only 5%, but the description compensates nearly fully. It explains the meaning and constraints of many parameters: withImage default true, cycleTimeUs conversion (us to 100ns ticks), priority range 0-255, affinity as TwinCAT hex token or named CPU masks, and the xml escape hatch being mutually exclusive with typed fields. This adds substantial value beyond the bare schema.

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

  Purpose5/5

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

  The description clearly states the tool manages RT tasks under TIRT, RT-core settings under TIRS, and linked tasks under TIPC. It lists specific actions and distinguishes itself from siblings by referencing specific subsystems (TIRT, TIRS, TIPC) and noting it is config-only with no confirm token needed, which is unique among sibling tools like tc_system or tc_tree.

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

  Usage Guidelines3/5

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

  The description implies usage through its detailed action list but does not explicitly state when to use this tool versus alternatives (e.g., tc_tree or tc_system). It mentions that runtime needs a later activate/restart and that TISC (safety) is untouched, but no direct comparison or when-not guidance is provided.

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

• tc_settingsA
  4.5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and delivers extensively. It discloses that all actions are offline-only with no runtime effect, that set_silent_mode has version dependency (TC3.1>=4020.0), that set_target_platform invalidates prior build output, that set_disabled only accepts 0/1 (not the derived read-only state 2), and that safety-rooted paths are rejected for certain actions. This level of detail goes well beyond basic expectations.

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

  Conciseness4/5

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

  The description is a single dense paragraph that packs substantial information without redundancy. Every sentence adds distinct value. However, it could be more scannable by using bullet points or action-based groupings, especially given the high number of actions. It is not overly verbose but slightly compromises readability for an AI agent.

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

  Completeness4/5

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

  Given the tool's complexity (10 actions, 7 parameters, no output schema, no annotations), the description covers purpose, usage, behavioral traits, and parameter semantics well. It explicitly describes the return format for get_disabled but does not mention return values for other get actions (e.g., get_silent_mode, get_target_platform, get_independent_file). This is a moderate gap; describing return types would make it fully complete.

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

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate. It adds meaning by explaining parameters in context of each action (e.g., 'file = absolute .tszip' for save_solution_archive, 'platform = "TwinCAT RT (x86)" | "TwinCAT RT (x64)"' for set_target_platform, 'path, enabled' for independent_file). It also clarifies that the 'disabled' parameter uses 0/1 values despite the boolean type, and explains 'name?' default behavior for save_plc_archive. However, it does not provide a systematic list of all parameters and their defaults, leaving some parameters (like 'enabled' for set_silent_mode) partially inferred.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: 'XAE engineering settings & packaging' and emphasizes it is OFFLINE/engineering-only with no runtime state changes. It lists all 10 actions explicitly, distinguishing the tool from runtime-impacting tools like tc_system. The purpose is specific and unambiguous, leaving no doubt about what the tool does.

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

  Usage Guidelines4/5

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

  The description provides clear context on when to use the tool (offline-only engineering settings) and includes key constraints (e.g., 'none are confirm-gated', 'parent dir must exist' for save_solution_archive). It also explains relationships between actions and other steps (e.g., switching platform invalidates build output, so rebuild before download). However, it does not explicitly name alternative tools for similar tasks, leaving some comparison implicit rather than explicit.

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

• plc_pouA
  4.6/5.0
  Behavior5/5

  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 and does so comprehensively. It describes the offline-only nature, in-memory edits with delayed runtime effect, guarded delete requiring explicit confirmation, refusal of TISC-rooted paths, caching behavior with self-invalidation, dirty-checking and file-save watcher for search, and the fact that graphical bodies are not text-editable (diagnostic only via get_graphical). It also notes that batch operations continue on error and return structured results with success rows. All critical behavioral traits are transparent.

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

  Conciseness3/5

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

  The description is very long and dense, packing a huge amount of information into a single block of text. It is structured by action category (CREATE, READ, WRITE, SURGICAL TEXT EDIT, DISCOVER, DELETE, LIFECYCLE, BUILD-CHECK) which helps navigation, but the lack of line breaks, bullet points, or headings makes it hard to scan quickly. Every sentence earns its place, but the overall conciseness suffers from the sheer volume. A little restructuring would improve readability without losing content.

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

  Completeness4/5

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

  Given the tool's high complexity (46 parameters, up to 28 enum actions, nested objects, no output schema), the description is remarkably complete. It covers all major action categories, parameter semantics, behavioral traits, ordering dependencies (e.g., list a parent folder entry before its child in create_folder_batch), and error handling (e.g., replace fails on count mismatch). The absence of an output schema is mitigated by describing return shapes in the text. However, some edge cases (e.g., what happens when move fails mid-operation) are not mentioned, and the caching details could be more precise about when refresh is truly needed.

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

  Parameters4/5

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

  Schema description coverage is 59%, meaning many parameters lack descriptions in the schema. The description compensates by explaining parameters in context for each action (e.g., subType values and their meanings, language enum values, range and grep usage for get_decl/get_impl, expectCount for replace, validate for surgical writes). However, some parameters like 'details', 'at', 'before' dual-type, and 'occurrence' are still only partially explained relative to the rich action set. Overall, the description adds significant meaning beyond the schema, but the schema itself still has gaps that are not fully covered.

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

  Purpose5/5

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

  The description begins by clearly stating 'PLC object authoring + code edit on the open solution,' which specifies the verb (author and code edit) and the resource (PLC objects). It thoroughly differentiates from siblings by emphasizing OFFLINE engineering only, tree path separators, and safety policy for TISC paths. This makes the tool's purpose unmistakable and distinct from building, downloading, or runtime tools like xae_build, plc_download, or twincat_restart_runtime.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use this tool ('OFFLINE engineering only') and when not to ('refuses TISC'). It provides detailed alternatives for specific operations (e.g., 'For code POUs prefer set_decl after create', 'read-modify-write cycle for surgical edits', 'cheap-first: outline for structure; get_decl/get_impl with grep or range'). It distinguishes between discovery, reading, writing, and lifecycle operations, and guides the agent on cost-saving strategies like using outline before full text, or search for content patterns vs find for path-by-name.

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

• plc_projectA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries full burden. It discloses many behaviors: guarded actions require confirm, default to no-op for generate_boot_project, online command envelope is UNVERIFIED, reset_* need prior login, install:true mutates local repository, subType 0 copy/1 move/2 use-in-place. However, it doesn't explicitly state whether these operations have side effects on runtime or persistence.

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

  Conciseness4/5

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

  The description is dense but front-loaded with context: tree path syntax and node significance first, then action list. Each action is compactly described with parameters in parentheses. However, the paragraph is long (over 20 lines) and could benefit from line breaks or bullet points for readability.

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

  Completeness5/5

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

  Given the complexity (16 parameters, 9 actions, no output schema), the description is remarkably complete. It covers all actions, parameter defaults, node distinctions, guarded behavior, online command specifics, and scope exclusions. No major gaps identified for project lifecycle tasks.

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

  Parameters4/5

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

  Schema description coverage is only 6%, so description must compensate. It defines parameter semantics for all 9 actions inline, e.g., 'create_from_template (name, template, before?, save?)' with plain-English explanation. It explains special defaults like 'treePath? = ROOT' and 'treePath? = INSTANCE' for different actions. However, some parameters like 'before', 'save', 'selection' lack detailed specs on their effects.

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

  Purpose5/5

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

  Description clearly specifies verb+resource: 'PLC (IEC) project lifecycle on the open solution.' It lists all 9 actions with specific purposes, distinguishing each (e.g., create vs open vs info vs online). The description differentiates from siblings like plc_download and plc_pou by focusing on project-level lifecycle actions.

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

  Usage Guidelines5/5

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

  Explicit when-to-use: 'Actions:' enumerate all operations. Provides critical context like node matters (ROOT vs INSTANCE), guarded actions requiring confirm='ALLOW_PLC_DOWNLOAD', and defaults (e.g., default no-op for generate_boot_project, default treePath for info and set_boot_flags). The description also states out-of-scope: 'Safety projects are deliberately out of scope.'

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

• plc_sessionA
  4.6/5.0
  Behavior4/5

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

  No annotations are provided, so the description must carry full transparency weight. It discloses read-only nature for 'status', logs the IDE out (destructive hint), applies deferred edits, and specifies that logout is guarded with a confirmation parameter. The only minor gap is not explicitly stating whether a successful login check or other prerequisites are needed before logout.

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

  Conciseness5/5

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

  The description is four sentences, each earning its place: first sentence sets context, second explains 'status', third explains 'logout' with side effects, fourth adds guard constraint. Front-loaded with the core mechanism. No redundant information.

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

  Completeness4/5

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

  Given 2 parameters, no output schema, and no annotations, the description covers the essential details (actions, side effects, guard). It is complete enough for an agent to use the tool safely. Minor gap: does not describe the return format for 'status' (e.g., exact structure of { loggedIn }).

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

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate entirely. It explains the 'action' enum values and their semantics, and documents the 'confirm' parameter purpose (guard for logout). Without the description, the agent would only see an enum and a string field. The description adds significant meaning, though it could hint at expected values for 'confirm' beyond the example given.

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

  Purpose5/5

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

  The description states specific actions ('status' for read-only login status, 'logout' for logging out), clearly identifies the resource (PLC session) and mechanism (UI Automation), and distinguishes from sibling tools by noting DTE commands are unavailable on 64-bit shell. This provides a specific verb+resource pairing with clear differentiation.

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

  Usage Guidelines5/5

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

  The description explicitly says when to use 'status' (read-only) vs 'logout', warns about side effects (applies source edits, never logs back in), and states a required guard ('confirm' field needed for logout). This gives clear context for tool selection and safe usage.

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

• tc_licenseA
  4.6/5.0
  Behavior5/5

  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 version-dependent behavior (older targets lack support, HRESULT surfaced), offline nature of 'add', guarded nature of 'activate_response' with confirm requirement, and the fact that 'add' only links to existing hardware. It also explains the raw parameter's effect and defaults for oemGuid. This is comprehensive behavioral disclosure.

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

  Conciseness4/5

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

  The description is long but packed with essential information; no sentence is wasted. However, it could be more structured using bullet points or separate sections for each action to improve readability. The version and safety notes are front-loaded, which is good.

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

  Completeness4/5

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

  Given the complexity (7 params, 3 actions, version dependencies, no output schema), the description covers most aspects: return format for 'list', prerequisites for 'add' and 'activate_response', and behavioral details. However, it does not explicitly state what the 'add' or 'activate_response' actions return, though the 'config-only' and 'state change' labels imply no return value. Minor gap.

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

  Parameters5/5

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

  The input schema has only 29% description coverage (2 of 7 parameters described). The description adds meaning for all parameters: raw (pass true for full blob), name (for add), device (dongle display-name or ObjectID), path (absolute path to response file), confirm (requires specific value), oemGuid (optional, defaults to 0). It also explains the action enum values. This fully compensates for the low schema coverage.

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

  Purpose5/5

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

  The description clearly states the tool handles TwinCAT licensing on the TIRC^License node and enumerates three specific actions (list, add, activate_response). It distinguishes from unrelated domains by explicitly noting it does not touch the safety system, and the sibling tool list includes many TwinCAT tools but the licensing focus sets it apart.

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

  Usage Guidelines4/5

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

  The description provides clear prerequisites: version requirements (TC3.1 >= 4022.4), for the 'add' action it directs to create the dongle terminal first via tc_ethercat/tc_tree, and for 'activate_response' it specifies the required confirm value and no-op default. It also implies not to use for safety. However, it does not explicitly compare to sibling tools or provide when-not-to-use scenarios beyond the safety exclusion.

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

• tc_moduleA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and delivers detailed behavioral traits: lists return structure, explains create error handling (ghost child cleanup), warns that XPath names for enable_symbols are unverified, and describes the guarded nature of set_context. All mutation effects are clearly stated.

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

  Conciseness4/5

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

  The description is long but well-structured: general scope first, then each action with its own details, followed by a caveat and cross-reference. While some redundancy exists (e.g., repeating the no-runtime-transition warning), the length is justified by the tool's multi-action nature. Slightly verbose for a single tool definition.

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

  Completeness4/5

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

  Given the high parameter count (13), low schema coverage, and no output schema, the description provides extensive context: return shape for list, error behavior for create, usage order for enable_symbols, and the guarded guard for set_context. However, return structures for get_xml, set_xml, enable_symbols, and set_context are only implied, leaving minor ambiguity for an agent.

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

  Parameters5/5

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

  Schema description coverage is only 15%, meaning the JSON schema provides almost no parameter context. The description compensates fully: explains the 'by' and 'id' semantics for create, describes 'path', 'xml', 'before', 'confirm', 'taskObjectId', 'contextId', and the boolean flags for enable_symbols. Much more detail than the schema.

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

  Purpose5/5

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

  The description clearly identifies the target resource ('TcCOM module objects under TIRC^TcCOM Objects') and enumerates specific actions (list, create, get_xml, etc.), all of which are distinct from sibling tools. It distinguishes itself from tc_link by directing DataArea wiring to that sibling.

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

  Usage Guidelines5/5

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

  Explicitly states config-time-only usage and what the tool does NOT do ('no INIT/PREOP/SAFEOP/OP transitions', 'nothing here activates config, downloads, or touches the runtime/safety system'). Provides alternative for DataArea symbol wiring via tc_link, and warns about set_context requiring a confirm flag.

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

• tc_routeA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It clearly marks read actions as 'unguarded — a transient search trigger, never persists a route' and write actions as 'GUARDED, require confirm, default NO-OP'. It explains side effects (route changes take effect in engineering project), build dependencies, and default timeout behavior. No contradictions or omissions.

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

  Conciseness4/5

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

  The description is dense and well-organized into READ vs WRITE sections with bullet-like formatting. Every sentence adds value. It is slightly longer than necessary due to inline parameter lists, but this is justified by the need to compensate for the lack of schema descriptions. The front-loading with the overall purpose is effective.

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

  Completeness5/5

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

  Given the tool's complexity (16 parameters, no output schema, no annotations, 24 siblings), the description covers critical contextual completeness: it explains the effect of operations, guard mechanism, build dependencies, action-parameter mapping, and scope limitation (config/engineering-side only). Return values are described inline for read actions. An agent has sufficient information to select and invoke this tool correctly.

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

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate. It does so by parameterizing each action in natural language (e.g., for add_route: 'remoteName, remoteNetId, one of remoteIpAddr|remoteHostName; optional userName/password/noEncryption/localName'). It explains the role of timeoutMs for broadcast_search and confirm for writes. A few parameters like host, name, netId are mentioned but not fully syntax-described for all actions; however, enough meaning is added to guide the agent.

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

  Purpose5/5

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

  The description explicitly states the tool 'ADS routes via the System Manager TIRR (Routes) node' and distinguishes between READ and WRITE operations with specific actions (list, broadcast_search, search_host, add_route, add_project_route). It is a specific verb+resource combination that clearly differentiates from sibling tools which cover other TwinCAT domains.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance for each action, including guard requirements for writes (confirm='ALLOW_TWINCAT_ROUTE_WRITE'), build prerequisites for search_host, and a clear note that route changes affect the project but not auto-activation. It also states what the tool does NOT do ('Nothing here targets the safety system'). This leaves no ambiguity for the agent.

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

• tc_treeA
  4.8/5.0
  Behavior5/5

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

  No annotations were provided, so the description carries the full burden. It fully discloses critical behavioral traits: the guard on delete (dryRun:true and confirm=

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

  Conciseness4/5

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

  The description is comprehensive but somewhat dense and could be more efficiently structured. It front-loads the path separator convention and batch-first principle, which is good. However, after that the actions are presented in a long running sentence that mixes group headers with individual actions. Breaking the actions into a bulleted list or clearer paragraph structure would improve readability. As is, it earns its sentences but is slightly harder to parse than necessary for an agent.

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

  Completeness5/5

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

  Given the tool's high complexity (20 parameters, 17 actions, no nested objects, no output schema, no annotations), the description is remarkably complete. It covers all actions, explains each batch form, warns about pitfalls (ghost entries for create without createInfo), and directs to the right sibling tool where appropriate. For a tool of this scope, the description leaves very few gaps—agents can reliably select the right action and understand the expected behavior.

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

  Parameters4/5

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

  Schema description coverage is only 5%, so the description must compensate. It adds significant meaning beyond the raw schema by explaining the purpose of key parameters: it describes the ^ path separator format (TIPC^MyPlc), the batch structures for each action (paths:[...], items:[{path,xml}], creates:[{parent,name,subType,before?,createInfo?}], etc.), what summary means for get_xml (compact identity + slot-module list), and what returnXml does for set_xml. However, not every parameter is covered in detail—some like 'reconnect' or 'subType' for single actions are not explained, preventing a perfect score.

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

  Purpose5/5

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

  The description clearly states the tool manages TwinCAT System Manager tree items, with a specific verb+resource structure. It lists all 17 actions (READ, WRITE, RENAME, CREATE, DELETE, etc.) and distinguishes the tool from siblings like tc_ethercat by explicitly stating that adding EtherCAT terminals should use the dedicated tool. The description provides a comprehensive overview that fully differentiates this tool from its siblings.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use and when-not-to-use guidance: it recommends using the *_batch actions for more than one item, and for adding EtherCAT terminals/boxes it directs users to the 'dedicated tc_ethercat tool'. It also explains the batch roll-up behavior and the dryRun/confirm guardrails for delete operations. This makes it very clear when to choose which form of the tool and when to use an alternative.

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

• tc_fieldbusA
  4.9/5.0
  Behavior5/5

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

  Given no annotations exist, the description carries full burden and meets it thoroughly. It discloses offline-only behavior, no confirm token needed, runtime activation requirement, safety path restrictions, batch behavior with roll-up error structure, and cleanup of ghosts on wrong subType/vInfo. It also notes unverified caveats like 'bare-number form is unverified and NOT shipped' and GSD box subType format needing confirmation.

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

  Conciseness4/5

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

  The description is dense and front-loaded with the core purpose, but its length (over 1000 words) is justified by the tool's complexity (10 actions, 28 parameters, multiple fieldbus types). Every sentence adds value, but the sheer volume could overwhelm an AI agent. A structured bullet format might improve scannability, but the current prose is functional.

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

  Completeness5/5

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

  Given the tool's high complexity (10 actions, multiple protocols, no output schema), the description provides all essential context: offline-only constraint, sibling differentiation, batch optimization, detailed subType mappings, caveats on unverified features, and parameter semantics for each action. There are no obvious gaps for the described functionality.

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

  Parameters5/5

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

  With only 7% schema description coverage and 28 parameters, the description compensates extensively. It documents each action's parameter usage inline (e.g., 'vInfo = gsdPath#moduleIdentNumber#boxFlags#dapNumber'), provides subType cheat-sheet for all fieldbus types, and explains purpose of action-specific parameters like claimIndex and importExtendedMessages. The description adds immense meaning beyond the bare schema.

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

  Purpose5/5

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

  The description explicitly states the tool creates and configures NON-EtherCAT fieldbus masters/slaves/boxes, listing specific protocols (PROFINET, PROFIBUS, CANopen, DeviceNet, EAP). It clearly distinguishes itself from sibling tc_ethercat by stating 'For EtherCAT terminals/boxes use tc_ethercat instead.' The verb+resource combination is highly specific.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use and when-not-to-use guidance. It states 'OFFLINE CONFIG ONLY — no confirm token needed; runtime needs a later activate/restart; TISC (safety) paths refused.' It directs toward create_batch for multiple devices and tc_ethercat for EtherCAT. This is comprehensive usage guidance.

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

• tc_measurementA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description bears full responsibility for behavioral disclosure. It reveals guarded operations (scope_record, logger_delete, stream_delete require confirm), experimental status of non-zero elementType, automatic suffix appending for stream nodes, and failure behavior ('clear message' if templates missing). 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.

  Conciseness4/5

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

  The description is comprehensive but lengthy (over 500 words). It is well-structured with action groups (scope_, analytics_, logger_, stream_) and uses colons to separate parameter details. However, it could be more concise by breaking into bullet points or separate sections without losing clarity.

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

  Completeness5/5

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

  Given the tool's complexity (17 parameters, 9 actions, no output schema, no annotations), the description is remarkably complete. It covers all actions, their parameter usage, guarded states, verification status, defaults, and explicitly lists omitted features. No critical gaps remain.

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

  Parameters5/5

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

  Schema description coverage is only 24%, but the description adds rich parameter semantics for each action: default values for template and destination, explanation of parentPath resolution, meaning of 'before' (insert before sibling), and dryRun usage. This significantly compensates for the sparse schema descriptions.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: managing TwinCAT measurement projects (Scope and Analytics) and TIAN logger/stream configuration. It distinguishes between project-level actions (AddFromTemplate) and tree node operations (CreateChild/DeleteChild), and explicitly differentiates from sibling tool tc_tree for raw XML operations.

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

  Usage Guidelines5/5

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

  The description provides explicit guidance on when to use this tool vs. alternatives, e.g., 'For raw ProduceXml/ConsumeXml on a TIAN logger/stream node ... use tc_tree get_xml/set_xml.' It also explains guarded actions requiring confirm, and mentions that analytics_create only creates the project, not network wiring, setting clear expectations.

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

• tc_variantA
  4.9/5.0
  Behavior5/5

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

  With no annotations provided, the description fully carries the burden of behavioral disclosure. It reveals that set_config replaces the whole variant definition, save:true triggers File.SaveAll, disable/enable affects the active variant, and that the readback disabled int may report SMDS_PARENT_DISABLED=2 (a read-only state never written). This is comprehensive behavioral context beyond what annotations would typically cover.

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

  Conciseness4/5

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

  The description is compact and front-loaded with the core purpose and prerequisites. It uses clear section breaks for actions. A slight deduction because the first sentence is dense and could be split: 'Project VARIANT management on the open solution (needs TCatSysManagerLib >= 3.3.0.0; older installs get_* return empty and set_*/disable surface a clear COM error).' This packs version, error behavior, and scope into one sentence, but remains readable.

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

  Completeness5/5

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

  Given the high complexity (5 parameters, 6 actions, no output schema, no annotations), the description covers prerequisites, offline-only nature, action semantics, parameter formats, error conditions, and readback quirks. It does not need to explain return values since there is no output schema, and it provides enough detail for an agent to invoke any action correctly.

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

  Parameters5/5

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

  Schema description coverage is 0% (only parameter names and types are in the schema, no descriptions). The description compensates fully by detailing each parameter: xml expects a raw <ProjectVariants> XML document with specific child elements, path uses ^ separators and must avoid TISC, variant can be a name or bracket-group, save is optional, and action is an enum explained per sub-action. This adds critical meaning to every parameter.

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

  Purpose5/5

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

  The description clearly states the tool manages project variants on a Beckhoff TwinCAT open solution. It lists six specific actions (get_config, get_current, set_config, select, disable, enable) and details each action's verb, resource, and behavior, distinguishing this tool from siblings like xae_build or tc_system.

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

  Usage Guidelines5/5

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

  The description explicitly says this is for OFFLINE CONFIG ONLY, warns that older installs return empty/errors, and clarifies when a confirm token is not needed but runtime activation is required later. It also notes that per-item disable/enable refuses safety (TISC) paths, providing clear when-to and when-not-to guidance.

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