Server Quality Checklist

Tool Scores

• simscale_selectC
  2.7/5.0
  Behavior2/5

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

  The description adds no behavioral context beyond the annotations. Annotations indicate readOnlyHint=false (a mutating action), but the description doesn't explain side effects, requirements (like visibility), or whether it works only on native selects. No contradiction with annotations, but no value added.

  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, short sentence with no fluff. It is front-loaded and minimal, which is concise. However, it may be too terse given the tool's nested parameter structure, but conciseness itself is good.

  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 two required nested parameters and no output schema, the one-line description is insufficient. It does not explain how to target the select control or how to specify the option, leaving the agent with incomplete information to invoke the tool correctly.

  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 50%, only the 'target' parameter has a schema description. The tool description adds nothing about parameters: it doesn't explain how to specify 'option' (by string, index, label, or value) or how to target the select. The description fails to compensate for the 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's function: 'Choose an option in a native SimScale select control.' The verb 'choose' and resource 'native SimScale select control' make the purpose specific. It implicitly distinguishes from siblings like simscale_click or simscale_fill, though it does not explicitly name alternatives.

  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 is provided on when to use this tool versus alternatives. The description does not mention any exclusions, prerequisites, or comparison to sibling tools like simscale_fill or simscale_click. Usage is only implied by the resource type.

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

• simscale_pressA
  3.7/5.0
  Behavior3/5

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

  The description adds the useful constraint that the target must be 'unique visible', which is additional context beyond the annotations. However, it does not disclose potential side effects of the key press (e.g., form submission, navigation, or state changes) or how failures are handled (e.g., when no unique match exists), leaving some ambiguity for a non-read-only action.

  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 a single, concise sentence that front-loads the action verb, includes relevant examples, and states constraints without any redundant phrasing. It is easy to read and understand.

  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 the small parameter count and existing annotations, the description adequately conveys the core purpose and constraints. However, it omits details about return values or success/failure behavior, and the lack of an output schema makes this omission more noticeable. The description is sufficient for basic use but could be stronger by noting what happens after the press.

  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?

  The schema already describes the 'target' object as a stable, visible UI target with preferred selectors, so the description adds limited value there. For the 'key' parameter, the description provides helpful examples ('Enter or Escape') that clarify expected values, but it does not specify key format or modifiers. Overall, the added meaning is moderate, balancing the partial 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 uses the specific verb 'Press' with a clear object (a keyboard key on a SimScale control) and provides examples like Enter or Escape, making the action unambiguous. It also distinguishes this tool from sibling interaction tools such as simscale_click and simscale_fill by focusing solely on key presses.

  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 whenever a keyboard interaction is needed, but it does not explicitly state when to prefer this tool over alternatives like clicking or filling, nor does it mention exclusions such as when a control is not visible or unique. The guidance is inferred from the action itself rather than clearly articulated.

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

• simscale_edge_statusA
  3.8/5.0
  Behavior3/5

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

  Annotations already declare this as read-only, idempotent, and non-destructive, so the safety profile is clear. The description adds the specific dual check (Edge running and signed-in status) but does not elaborate on what 'appears signed in' means or any additional behavior. It is consistent 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.

  Conciseness5/5

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

  A single, well-structured sentence that front-loads the action and states both conditions. No wasted words.

  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 simple, zero-parameter status check with robust annotations (read-only, idempotent), the description is sufficient to understand what the tool does. It does not specify return format, but no output schema exists and the tool name implies a status result, so this is not a significant gap.

  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 tool has zero parameters, so the schema is trivially covered. The description provides no parameter-specific details, but baseline for 0 params is 4, and the description clarifies the semantic scope of the check.

  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 uses a specific verb ('Check') and clearly identifies the scope: whether Edge is running and whether the current SimScale page appears signed in. This distinguishes it from sibling tools like simscale_edge_start or simscale_page_state.

  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 is provided on when to use this tool versus alternatives. It does not mention that it should be used before starting Edge or to verify login state, nor does it exclude cases where simscale_page_state might be more appropriate.

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

• simscale_wait_for_textA
  3.8/5.0
  Behavior3/5

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

  The annotations already declare readOnlyHint=true and destructiveHint=false, disclosing the safety profile. The description adds that it waits for visible text, but it does not disclose what happens on timeout (e.g., throws an error) or whether it returns any value. Given the existing annotations, the description is adequate but not rich in behavioral detail, warranting a 3.

  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 a single, focused sentence. It front-loads the core action ('Wait for visible SimScale text') and adds a useful use-case clause. Every word contributes meaning, with no redundancy or unnecessary detail.

  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 wait tool, the description covers the purpose and typical scenarios. However, it does not explain timeout behavior or failure semantics, which are critical for an agent to know whether the action will block or error. The schema has timeout_ms, but the description does not integrate it. This leaves a noticeable gap for a complete understanding.

  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 implicitly clarifies that the 'text' parameter refers to the visible text to wait for, but it says nothing about 'timeout_ms', its default, or its meaning as a maximum wait duration. The schema provides names and constraints, but the description falls short of fully clarifying parameter semantics.

  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 function: "Wait for visible SimScale text". This is a specific verb+resource combination that distinguishes it from sibling tools like click, fill, or screenshot, which perform different UI actions. It also provides context on when it's useful (CAD imports, meshing, run status transitions), making its purpose unambiguous.

  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: "useful for CAD imports, meshing, and run status transitions" suggests when to invoke this wait tool. However, it does not explicitly mention when NOT to use it or name alternative tools. Since sibling tools include page_state and edge_status which might be used for checking state, the lack of exclusions keeps it at 4 rather than 5.

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

• simscale_fillA
  4/5.0
  Behavior4/5

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

  The description discloses a key behavioral trait: password fields are blocked and require manual entry. This goes beyond the annotations (which only indicate mutation and non-idempotency) by revealing a specific limitation. It does not contradict annotations, and it adds context about how the tool behaves for a certain field type.

  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 two short sentences. The first sentence states the core function and the second adds a critical limitation. There is no filler or redundant information. It is very concise and front-loaded.

  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?

  The description conveys the main action and a limitation, but it omits details about error behavior (e.g., what happens when a field is not unique or not visible), return values (there is no output schema), and how the value parameter should be used. Given the moderate complexity (nested target object) and lack of output schema, the description is adequate but has clear gaps.

  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?

  The tool description adds no explanation of the parameters. The schema provides a description for 'target' ('A stable, visible UI target...') but 'value' is only typed as a string with no guidance. The description could compensate for this gap but doesn't, leaving the agent to infer what 'value' means and how it might be formatted.

  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 action: 'Fill one unique visible SimScale field.' It specifies a specific verb (fill), a resource (SimScale field), and adds constraints (one, unique, visible). This distinguishes it from sibling tools like simscale_click or simscale_press, and the note about password fields adds clarity about what it does (and doesn't) handle.

  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 gives an explicit exclusion: 'Password fields are blocked and must be completed manually in Edge.' This tells the agent when not to use this tool. However, it does not explicitly mention when to use it or compare it to alternatives (such as simscale_press for keyboard input), making it clear but not fully comprehensive.

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

• simscale_page_stateA
  4/5.0
  Behavior5/5

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

  The description adds significant behavioral context beyond the annotations. It discloses that the tool reads headings, notices, and interactive controls, and explicitly guarantees it does not expose passwords or cookies — a security-relevant trait. This goes beyond the readOnlyHint and idempotentHint, which only state that it is non-mutating and idempotent. No contradiction with annotations.

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

  Conciseness5/5

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

  The description is a single, well-structured sentence that leads with the verb. It is appropriately sized, contains no fluff, and every phrase adds value (e.g., 'without exposing passwords or cookies' is a meaningful qualifier).

  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 the simple one-parameter schema and strong annotations, the description covers the core purpose well. However, it does not clarify the return format or the meaning of max_items, and there is no output schema to compensate. This makes it adequate but not fully complete for an agent to understand the full behavior without further inference.

  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?

  The input schema has one parameter (max_items) but no description, and the schema description coverage is 0%. The tool description does not mention this parameter at all, leaving the agent to guess what 'items' refers to and how the limit affects results. Since the description was supposed to compensate for the missing schema documentation, it fails to provide meaningful parameter semantics.

  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 uses the specific verb "Read" and clearly identifies the resource: the current SimScale page's headings, notices, and visible interactive controls. It also explicitly states what is excluded (passwords and cookies), which distinguishes it from other tools like simscape_screenshot or simscape_navigate. This is a clear, specific, and non-tautological statement.

  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 its usage as a read-only observation tool, especially since it is surrounded by action-oriented siblings like simscale_click and simscale_fill. However, it does not explicitly state when to use it over alternatives (e.g., screenshot) or provide exclusions for when not to use it. The usage guidance is implied rather than explicit.

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

• simscale_upload_fileA
  4.1/5.0
  Behavior4/5

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

  Annotations already indicate non-readOnly, non-idempotent, non-destructive. The description adds valuable context about the file root, visible input requirement, and mandatory confirmation, without contradicting the annotations.

  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?

  Two sentences, front-loaded with the action, and no redundant wording. 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?

  The description covers the core action and key constraints, but with a complex target object and no output schema, it leaves gaps on how to choose among target properties (test_id, role+name, label) and what the result looks like.

  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 coverage is only 33% (target has a description). The description adds meaning for file_path (from SIMSCALE_FILE_ROOT) and confirm_upload (safety confirmation), but does not elaborate on target property selection, leaving the nested object partially unexplained.

  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 a specific verb ('Upload') and resource ('CAD or other local file'), plus the source ('from SIMSCALE_FILE_ROOT') and destination ('through a visible file input'). This distinguishes it from siblings like simscale_click or simscale_fill.

  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 doesn't explicitly mention alternatives, but it provides clear context: upload from a specific root via a visible input, and requires confirm_upload=true. Since no sibling tool handles uploads, this is sufficient guidance.

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

• simscale_clickA
  4.2/5.0
  Behavior4/5

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

  The description adds useful behavior beyond annotations: it requires a 'unique visible' element and mandates confirm_action=true for mutating/compute labels. It does not contradict the annotations (readOnly, destructive hints) and provides actionable context, though it omits details on failure modes or return values.

  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?

  Two sentences, front-loaded with the primary action, and every word adds value. The structure is clear and elegantly efficient.

  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 simplicity (2 params, no output schema), the description covers the essential behavior and the key conditional (confirm_action). It doesn't detail error handling or multiple-match scenarios, but the openWorldHint and sibling context suggest a broader framework, so this is acceptable.

  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 description explains the confirm_action parameter's role (required for mutating/compute labels), adding meaning beyond the schema which only gives a default. The target parameter is partially described in the schema, and the description recaps key selectors (role, label, text, test ID) without duplicating all details, compensating for the 50% 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 action (click), the target resource (SimScale control), and the selection criteria (role, label, text, or test ID). 'Unique visible' adds precise scope, and the confirmation requirement distinguishes it from sibling tools like simscale_press or simscale_fill.

  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 when to use (when clicking a control) but does not explicitly direct users away from alternatives or mention when not to use. It mentions the confirm_action requirement for mutating/compute labels, which is a conditional, but no comparison with sibling tools.

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

• simscale_downloadA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare non-read-only and non-idempotent behavior. The description adds valuable context: the file save location (SIMSCALE_FILE_ROOT/simscale-downloads) and the confirmation requirement. This goes beyond the structured annotations without contradicting them.

  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 two sentences, front-loads the primary action, and gives the save destination and a required flag. No unnecessary words or repetition.

  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 download tool with two parameters (one nested object well-described in schema) and no output schema, the description covers the essential information: purpose, save location, and required flag. It lacks details like error handling or overwrite behavior, but these are not critical given the tool's simplicity and annotation context.

  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 50%, and the description compensates by explaining confirm_download (must be true). The target parameter is already described in the schema as a stable, visible UI target with preferred locators. The tool description's reference to a 'unique SimScale download control' reinforces the target's purpose.

  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 function: clicking a unique SimScale download control and saving the result under a specific path. It distinguishes itself from sibling tools like simscale_click by specifying the download-and-save behavior.

  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 conveys a requirement (confirm_download=true) and implies use for downloading a SimScale control, but it does not explicitly mention when to use this tool over alternatives like simscale_click or how to decide between them. No exclusions or alternative tool references are provided.

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

• simscale_edge_startA
  4.2/5.0
  Behavior4/5

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

  Annotations already indicate openWorldHint, but the description adds valuable context: the profile is 'persistent' and manual login may be required. This goes beyond the structured hints and provides actionable behavioral expectations.

  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 only two sentences, front-loaded with the action verb 'Open,' and contains no redundant information. Every word contributes meaning.

  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 simplicity, the description covers the essential start behavior and a key manual step. It doesn't address what happens if already open, but sibling tools like status/close provide that context, so it's adequately 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?

  With zero parameters and 100% schema coverage, the description doesn't need to explain parameters. It adds relevant context about the profile and login, which is sufficient for a parameterless tool.

  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 uses the specific verb 'Open' with the resource 'SimScale in a persistent Microsoft Edge profile,' clearly distinguishing it from sibling tools like simscale_edge_close or simscale_edge_status. It is unambiguous and action-oriented.

  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 the tool is for starting the browser but does not explicitly state when to use it versus alternatives, nor does it mention exclusions (e.g., 'if already open, use simscale_edge_status'). The context is clear but lacks explicit guidance.

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

• simscale_navigateA
  4.2/5.0
  Behavior3/5

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

  The description adds useful constraints (HTTPS and SimScale domain restriction) beyond the annotations, which only state readOnlyHint=false and openWorldHint=true. It does not disclose what happens on failed navigation or whether it waits for page load. Given the sparse annotations, the description carries some burden but leaves room for more behavioral detail.

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

  Conciseness5/5

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

  The description is two short sentences, front-loaded with the primary action, and every word adds value. The 'Other domains are blocked' clause is essential and not redundant.

  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 simple one-parameter navigation tool with no output schema and minimal annotations, the description is sufficiently complete. It states the action, target, and restrictions. It could mention whether navigation is synchronous or returns a page state, but siblings like simscale_page_state suggest that is separate. Overall, complete for the tool's complexity.

  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 specifying that the 'url' parameter must be an HTTPS SimScale URL and that other domains are blocked, giving the parameter clear semantic constraints beyond the bare schema (type string, minLength 1).

  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 action ('Navigate Edge') and the specific resource/target ('HTTPS SimScale URL'). It distinguishes this from sibling tools like simscale_click or simscale_fill by pinpointing navigation as the sole purpose, and adds a scope restriction with 'Other domains are blocked.'

  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 gives clear context for when to use: for navigating to HTTPS SimScale URLs. It also provides an explicit exclusion ('Other domains are blocked') which is a when-not condition. No alternative tool is named, but among the siblings this is the only navigation tool, so usage is well implied.

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

• simscale_screenshotA
  4.2/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description adds useful context by specifying the scope ('current visible viewport') and output format ('PNG image'), but it does not disclose how the image is returned (e.g., file path, base64, URL) or any edge-case behavior. This is a moderate addition beyond annotations.

  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 a single, concise sentence that is front-loaded with the verb 'Capture.' Every word contributes to the meaning, with no redundancy or filler. It efficiently communicates the tool's purpose and output format.

  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 simplicity (0 parameters, no output schema), the description is largely complete for an agent to understand its core function. The primary gap is the lack of explicit detail on the return value (e.g., how the PNG is delivered), but for a screenshot tool in a browser automation context, this may be implicit. Annotations provide safety context, so the description adequately covers the essentials.

  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 tool has zero parameters, so the input schema coverage is trivially 100%. The baseline for 0-parameter tools is 4, and the description does not need to add parameter details. It appropriately focuses on the tool's behavior without referencing non-existent parameters.

  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 function: 'Capture the current visible SimScale viewport as a PNG image.' It uses a specific verb ('Capture'), specifies the resource (visible SimScale viewport), and the output format (PNG image). This distinguishes it from sibling tools that perform actions like navigation, clicking, or filling.

  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 for when to use the tool: when a screenshot of the current viewport is needed. It doesn't explicitly mention alternatives or exclusions, but the purpose is unambiguous given the sibling tools are all interaction actions. No alternative screenshot tool exists among siblings, so there's no confusion about when to use it.

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

• simscale_edge_closeA
  4.3/5.0
  Behavior4/5

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

  The annotations already indicate idempotent, non-destructive, and non-read-only behavior. The description adds that the login profile persists, providing useful context about the tool's side effects beyond the annotation fields. No contradiction.

  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 two concise sentences, front-loaded with the action, and adds contextual information about login persistence without unnecessary detail.

  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 simple no-parameter tool with no output schema, the description is complete. It states the action, the managed resource, and the key behavioral detail (profile persistence), which is sufficient for an agent to invoke it 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?

  This tool takes no parameters, and the schema fully covers this (100% coverage). The description does not need to explain parameters, and the baseline of 4 applies.

  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 action ('Close') and the target ('MCP-managed Edge window'), distinguishing it from sibling tools like edge_start and edge_status. It is specific and unambiguous.

  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 when to use this tool (to close the Edge window) but does not explicitly state alternatives or exclusions. The note about persistent login provides context but not explicit guidance on when to choose this tool over others. Usage is implied rather than stated.

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