Server Quality Checklist

Tool Scores

• get_session_statusA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint and openWorldHint. The description adds 'no input side effects' and lists returned fields, providing context beyond annotations without 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?

  Two sentences: first defines the tool's output, second gives usage and safety. Front-loaded, no unnecessary words.

  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 fetch tool with one parameter and no output schema, the description lists all returned fields and provides usage context. No gaps.

  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 100% with a clear description for session_id. The description mentions 'session metadata' but does not add new semantics beyond what the schema provides.

  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 'Fetch' and the resource 'session metadata', listing specific fields like status, host, mode. It distinguishes from sibling tools by emphasizing read-only nature and use case for metered time or checking active status.

  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?

  Explicitly states when to use: 'to tell the user about metered time or confirm the session is still active before more actions.' Lacks explicit when-not-to-use or alternatives, but the context is clear given sibling tools.

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

• get_live_view_urlA
  4.4/5.0
  Behavior5/5

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

  Beyond the readOnlyHint annotation, the description explicitly states the agent cannot access the console via API key and that the owner must be signed into Glasswarp. This provides critical behavioral context not available from annotations alone.

  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 brief and front-loaded with the essential action, using three focused sentences without unnecessary detail. Every sentence adds value.

  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 (one parameter, no output schema), the description is largely complete. It could optionally mention that it returns a URL string, but this is implicit and not required.

  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 single parameter 'session_id' is fully described in the schema (100% coverage). The tool description does not add additional semantics beyond the schema, resulting in a neutral 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 it returns the console Live View URL for the rig owner, specifying the exact resource and action. It distinguishes itself from sibling tools like 'observe' or 'get_session_status' by focusing on a high-frequency live view for human intervention.

  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 advises offering the tool on 'long or sensitive tasks' and notes it is read-only, giving clear context for use. It lacks explicit alternatives but the purpose is narrow enough that the 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.

• get_demoA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and openWorldHint=false. Description adds context that the tool does not execute or control a PC, which is helpful beyond annotations. No contradictions.

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

  Conciseness5/5

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

  Two sentences with no wasted words. Purpose is stated first, then critical non-behavior, then usage conditions, then output handling. Every sentence earns its place.

  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 read-only retrieval tool with 2 enum parameters and no output schema, the description provides all necessary context: what it does, when to call, what to do with the result, and what it is not. Complete.

  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 100% with clear descriptions for both parameters (demo_id enum, format enum). Description adds no new parameter detail beyond reinforcing that demo_id comes from list_demos, which is already implied.

  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?

  Clearly states 'Return one showcase run contract' with specific verb and resource, and explicitly distinguishes from execution ('Does NOT execute the demo or control a PC'). Differentiates from sibling 'list_demos' by describing what it returns.

  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?

  Provides explicit when-to-use ('Call after list_demos when you know the demo_id') and action-oriented guidance based on client capability ('If the client can run shell, offer the command; if chat-only, show the card'). Also warns against misuse ('Do not replace this with a slow MCP click loop for solver demos').

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

• launch_appA
  4.5/5.0
  Behavior5/5

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

  Exceeds annotations by detailing side effects: starts a process, Glasswarp tracks it and closes it on end_session. Annotations only indicate openWorldHint and destructiveHint; the description adds specific lifecycle and usage behavior (wait after launch), which is highly valuable for an agent.

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

  Conciseness5/5

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

  Four sentences, front-loaded with purpose, side effects, usage examples, and a critical caveat. Every sentence contributes unique information with no redundancy or fluff.

  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 no output schema, the description adequately covers purpose, side effects, parameter semantics, and usage guidance. No significant gaps remain for an agent 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.

  Parameters3/5

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

  Schema description coverage is 100%, so baseline is 3. The description adds minimal extra meaning: clarifies path_or_name can be name on PATH or absolute path, and mentions optional args, but schema already provides examples for args. Doesn't substantially improve understanding beyond 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 verb 'launch' with a specific resource ('executable on the remote Windows rig') and includes examples (notepad.exe, mspaint.exe, chrome) that distinguish it from sibling tools like click_target, type_text, etc.

  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?

  Provides explicit usage context ('Use for notepad.exe, mspaint.exe, chrome with URL args, etc.') and a critical behavioral guideline ('Wait/re-observe after launch before clicking — do not assume the window is focused immediately'). Could be improved by explicitly stating when not to use, but the examples and sibling list imply alternatives.

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

• list_demosA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true; description reinforces with 'Read-only catalog' and adds extra transparency about not starting sessions, touching rigs, or running solvers. No contradictions.

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

  Conciseness5/5

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

  Three concise sentences with front-loaded key information. Every sentence adds value.

  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?

  With annotations present, one fully documented parameter, and description covering purpose, usage, and behavior, the definition is complete for a simple list tool.

  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 covers the single parameter 'format' with enum and description. Description does not add further meaning beyond schema, so baseline of 3 is appropriate.

  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 it lists showcase run contracts with specific fields (id, title, install, command). It distinguishes from siblings by mentioning get_demo for one full card and list_rigs for UI work.

  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 tells when to use (user asks for demos or needs the command) and when not to (does not start session, touch rig, or run solvers). Provides alternatives: get_demo for one card, list_rigs → start_session → observe for ad-hoc UI.

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

• scrollA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate destructive hint and open world, but the description adds specific side effect ('scroll on whatever is under that point') and delta direction. 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?

  Four sentences, no fluff, front-loaded with core action and side effect, then direction and guidelines. Every sentence earns its place.

  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 no output schema and moderate complexity, the description covers all key aspects: behavior, side effect, parameter semantics, usage alternatives, and post-action caution. Highly complete.

  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 100% and each parameter is already well described. The description adds ordering ('move cursor then apply delta'), but this is implied by schema descriptions already stating 'hover before scrolling'. Minimal additional value.

  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 (move and scroll) and resource (cursor/page), and distinguishes from siblings by mentioning 'Prefer send_actions when scroll is part of a multi-step sequence.'

  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 when to use this tool (scroll on whatever under point) and when not to (prefer send_actions for sequences), plus a caution to re-observe after scrolling.

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

• type_textA
  4.6/5.0
  Behavior4/5

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

  Annotations already indicate destructiveHint=true, so the tool's mutability is known. The description adds context: it types via native input, has a side effect of keystrokes on the remote desktop, and does not click first. This enriches the behavioral profile 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 extremely concise (3 sentences) with no wasted words. It front-loads the main action, then adds prerequisite, side effect, and alternative usage, all in a logical order.

  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 action, prerequisite, side effect, and alternative. It lacks explicit mention of error behavior if the field is not focused, but that is implied as a prerequisite. Overall adequate for effective use.

  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 100% with clear descriptions for both parameters. The description adds that the text is a Unicode string and that it's literal (not a key combo), which adds meaning beyond the schema for the 'text' 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 types a Unicode string into the focused control via native input, which is specific and distinguishes it from siblings like send_keys (key combos) and send_actions (sequences). It explicitly says it does not click first and that for form fills, send_actions is preferred.

  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: focus the field before calling (using click_target or send_actions), and for multi-step form fills, prefer send_actions. This clearly tells when and when not to use this tool.

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

• click_targetA
  4.7/5.0
  Behavior5/5

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

  Discloses real mouse click side effect and the need to re-observe after screen change, adding context beyond annotations' destructiveHint.

  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?

  Four sentences, front-loaded with core action, no fluff – every sentence adds value.

  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?

  Covers purpose, usage guidelines, behavioral traits, and caveats comprehensively; no output schema 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 coverage is 100%, so parameters are already well documented. Description adds minimal extra semantics ('uses native center coords' but not tied to a specific parameter). Baseline 3 appropriate.

  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?

  Clearly states 'Left/right/middle-click a UIA target by id from the latest observe (uses native center coords)', specifying verb, resource, and special behavior. Distinguishes from sibling click_xy.

  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 prefers over click_xy, advises using send_actions for sequences instead of chaining, and warns against reusing stale target_ids – clear when-to-use and alternatives.

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

• end_sessionA
  4.7/5.0
  Behavior5/5

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

  Description lists specific side effects (stops billing, safety_restore, closes apps) beyond annotations, which already include destructiveHint and openWorldHint. Also notes that further calls on session_id will fail.

  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?

  Three sentences cover purpose, side effects, and usage guidelines with no fluff. Front-loaded key action.

  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 destructive tool with one parameter and no output schema, the description is complete: it covers what it does, side effects, when to use, and consequences of misuse.

  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?

  Only one parameter with full schema coverage and description. The tool description does not add additional semantic meaning beyond what the schema provides, but no extra info is needed.

  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 states 'End an active session' with specific verb and resource. It distinguishes from sibling tools like start_session by being the explicit counterpart.

  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 when to call ('when finished or abandoning') and warns not to call twice. Provides clear usage context without needing alternatives.

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

• send_keysA
  4.7/5.0
  Behavior5/5

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

  Annotations already convey destructiveHint and openWorldHint. The description adds 'Side effect: real key events on the remote desktop,' which provides additional behavioral context 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?

  Three sentences, each essential: what it does, side effect, and usage guidance. Front-loaded with the core action, no wasted words.

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

  Completeness5/5

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

  Simple tool with no output schema; the description fully covers purpose, side effects, and when to use alternatives. No gaps remain for an agent to misinterpret.

  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 100% with both parameters well-described. The description repeats examples from the schema but does not add significant new meaning beyond what the schema already provides.

  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 ('Send') with a clear resource ('key or chord to the focused window'), includes examples (enter, tab, ctrl+s), and distinguishes from sibling tools like type_text and send_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?

  Explicitly states when to prefer send_actions (when shortcut follows click/type in same sequence) and when to use type_text (for literal strings), providing clear decision guidance.

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

• click_xyA
  4.9/5.0
  Behavior5/5

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

  Discloses the side effect of a real mouse click on the remote desktop, which adds value beyond the destructiveHint annotation. 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?

  Two sentences with zero wasted words. Every sentence provides critical information (purpose, usage, warnings).

  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 click tool with 5 parameters, all well-described in schema, the description covers when to use, side effects, and coordinate system. No output schema 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 coverage is 100%, but the description adds important context about native coordinates and the prohibition of JPEG/downscaled coords, which enhances understanding 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 clearly states the tool clicks at native screen coordinates and distinguishes it from the sibling click_target by noting it's a last resort when no UIA target exists.

  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 says to prefer click_target when possible and warns against using JPEG or downscaled pixel coordinates, providing clear when-to-use and when-not-to-use guidance.

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

• dragA
  4.9/5.0
  Behavior5/5

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

  Discloses the side effect (mouse_down → moves → mouse_up on remote desktop) beyond the annotations' destructiveHint and openWorldHint, giving the agent full behavioral understanding.

  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 core action and purpose, followed by side effect and usage guidance. Every sentence is informative with no wasted words.

  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?

  No output schema, but the description thoroughly explains the drag operation, its side effects, and usage context. With 100% schema coverage for parameters, the definition is complete for an agent to select and invoke the tool correctly.

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

  Parameters4/5

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

  Schema description coverage is 100%, so baseline is 3. The description adds value by clarifying that coordinates are in 'native capture' space, which provides context beyond the schema defaults.

  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 states the action (press-move-release mouse drag) and resource (native capture coordinates), listing specific use cases like drawing, sliders, selection boxes, and drag-and-drop, which distinguishes it from 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?

  Explicitly states when to use this tool (for drag operations) and when to prefer send_actions for longer predictable sequences, providing clear guidance on alternatives.

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

• list_rigsA
  4.9/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint: true and openWorldHint: true. The description reinforces this with 'Read-only — does not start a session.' It also adds context about the USABLE flag meaning and the required user actions for non-usable rigs. 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.

  Conciseness5/5

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

  The description is concise: four sentences, each essential. The first sentence states the purpose and output. The second emphasizes read-only nature. The third provides ordering instruction. The fourth explains USABLE and failure response. No filler, well-structured.

  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?

  The tool has zero parameters and no output schema. The description fully compensates by listing the output fields, explaining the USABLE condition, and providing error-handling guidance. It covers all necessary context for an agent to use this tool correctly.

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

  Parameters4/5

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

  The input schema has zero parameters (schema_description_coverage 100%). With no parameters, the baseline is 4. The description adds value by explaining the output fields and their meaning (id, name, online, etc.), which is not in 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 the verb 'List', the resource 'Windows machines (rigs)', and the scope 'paired to this API key'. It lists the returned fields (id, name, online, api_access_enabled, USABLE). This clearly distinguishes it from sibling tools like start_session and end_session.

  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 usage guidance: 'Call first before start_session.' It explains the USABLE condition (online AND api_access_enabled) and tells the agent what to do if none are USABLE (instruct user to install agent, pair, and enable access). No alternative tools are mentioned, but the guidance is complete for this tool's context.

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

• send_actionsA
  4.9/5.0
  Behavior5/5

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

  Describes side effects (all actions execute on remote desktop), fail-fast behavior, and default observe_after behavior. Annotations include destructiveHint and openWorldHint, but the description adds meaningful context beyond those without 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 well-structured, starting with the core purpose, then side effects, then usage guidelines. Every sentence adds value with no filler, and it's appropriately sized for 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?

  Given the tool's complexity (multi-step actions, side effects, defaults), the description covers all necessary aspects: purpose, usage boundaries, side effects, and guidance on alternatives. No return value explanation needed as no output schema is present.

  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 100% so parameters are already documented, but the description adds useful semantic detail about defaults (observe_after defaults true) and conditional behavior (observe_image for JPEG). This goes beyond mere schema repetition.

  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 tool as a multi-step action batcher supporting 1-10 predictable UI actions, lists supported action types, and explicitly distinguishes from single-action sibling tools (e.g., 'Prefer this over chaining solo click/type/keys tools').

  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?

  Provides explicit guidance on when to use (batch predictable actions) and when not to ('Do not batch across unpredictable waits...'), along with a clear alternative (single-step those). This directly helps the agent select the correct tool.

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

• start_sessionA
  4.9/5.0
  Behavior5/5

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

  Discloses side effects beyond annotations: wall-clock billing, on-screen indicator, enabling observe/input, and idle auto-end after ~15 minutes. No contradiction with annotations (destructiveHint, openWorldHint).

  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?

  Four sentences cover all essential information with no redundancy. Critical points are front-loaded.

  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?

  Covers prerequisites, side effects, idle timeout, required follow-up (end_session), and return values (session_id, Live View URL). No output schema exists, but description provides sufficient guidance.

  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 rig_id with a clear description. The description adds context that the rig must be 'USABLE' and from list_rigs, reinforcing selection criteria 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?

  Clearly specifies the action ('Start'), resource ('metered desktop session'), and target ('USABLE rig from list_rigs'). Differentiates from sibling tools like end_session, which ends the session.

  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 when to call (when a USABLE rig exists) and when not to call, and mandates calling end_session upon completion. Mentions prerequisite list_rigs and side effects that affect usage decisions.

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

• observeA
  5/5.0
  Behavior5/5

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

  Beyond readOnlyHint and openWorldHint annotations, the description details behavior (no mouse/keyboard, default image false, quality/max_width defaults, changed flag handling, target id validity).

  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?

  Concise and well-structured: front-loaded with purpose, each sentence adds necessary information, no redundancy.

  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?

  Comprehensive despite no output schema; covers return format, edge cases (changed=false, dirty null), and usage context effectively.

  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?

  Adds meaningful context to all parameters (e.g., when to set image=true, mark default, quality/max_width defaults, changed flag behavior) beyond the 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 reads the current screen returning UIA targets and a text summary. It specifies it does not move mouse/keyboard, distinguishing it from action tools.

  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?

  Provides explicit guidance: prefer send_actions for multi-step UI, observe after meaningful steps, conditionally set image=true, and handle changed=false by not re-analyzing.

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