Glasswarp

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

Describes side effects (starts process, tracked by Glasswarp, closed on session.end) and warns about focus assumption. Annotations already indicate destructiveHint and openWorldHint, so description adds useful 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.

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

Two sentences, no fluff. Front-loads the action and parameter info, then adds crucial usage guidance. Every sentence earns its place.

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

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

With output schema present (not shown but mentioned), description explains side effects, use cases, and post-launch behavior. Sufficient for the tool's complexity.

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

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

All three parameters have schema descriptions (coverage 100%). Description adds context about optional args and mentions 'name on PATH or absolute path', which is already in the schema. Examples provide slight additional clarity but no essential new information.

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

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

Clearly states the action (launch) and resource (executable on remote Windows rig), with examples like notepad.exe, mspaint.exe. Distinguishes from sibling tools which are mostly input/screen/session related.

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

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

Provides explicit use cases (notepad.exe, chrome with URL args) and a post-launch behavior warning (do not assume window focused). However, does not explicitly state when not to use or alternatives.

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

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

Annotations already declare readOnlyHint=true, and the description reinforces that this tool does NOT execute demos or control a PC. It adds behavioral context about the return type (contract) and usage, but does not describe all behaviors like error handling or rate limits.

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

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

The description is extremely concise with four focused sentences. Each sentence adds unique value: purpose, negation of execution, usage guidance, and a warning. No unnecessary words.

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

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

For a simple read-only tool with 2 parameters and presence of an output schema, the description covers the core purpose, usage order, and output interpretation. It lacks explicit error handling or edge cases, but the output schema likely fills remaining gaps.

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

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

The schema description coverage is 100%, so baseline is 3. The description adds value by contextualizing the demo_id parameter as coming from demos.list, and implicitly linking format to user interaction style (shell vs chat-only). This goes beyond just repeating schema info.

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

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

The description uses a specific verb 'Return' and clearly identifies the resource as 'showcase run contract' with details (install, command, needs, framing). It explicitly distinguishes itself by stating what it does NOT do (execute or control a PC), ensuring no confusion with sibling tools.

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

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

The description provides clear guidance on when to call this tool ('after demos.list when you know the demo_id') and how to use its output (offer command if shell, show card if chat-only). It also warns against misuse, but does not explicitly list alternative tools for different scenarios.

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

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

Beyond the readOnlyHint annotation, the description adds key behavioral constraints: does NOT start a session, touch a rig, or run solvers. No contradiction found.

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

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

Description is concise with three sentences, front-loading the primary purpose and immediately adding usage guidance. No extraneous information.

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

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

Given the presence of an output schema and clear annotations, the description covers purpose, usage, and behavioral constraints thoroughly. No gaps identified.

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

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

Schema has 100% coverage with one parameter (format) with enum options and description. The description does not add new semantic information beyond the 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.

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

Description clearly states it lists showcase run contracts with specific fields (id, title, install, command). It distinguishes from siblings by mentioning demos.get for one full card and lists other tools for ad-hoc workflows.

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

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

Explicitly states when to use: when user asks for Minesweeper/Mona Lisa/Paint demos or needs the glasswarp-demo command. Also provides clear alternatives: prefer demos.get for one card, and for ad-hoc UI work use rigs.list → session.start → screen.observe.

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

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

Annotations already include destructiveHint=true. The description adds specific behavioral context: 'Side effect: real mouse click on the remote Windows desktop' and warns about target_id reuse. This goes beyond annotations but still could mention response behavior.

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

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

The description is concise with 4 sentences, front-loaded with the core action. Every sentence adds value: purpose, preference, side effect, caution, and alternative usage pattern. No wasted words.

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

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

Given the annotations and output schema (present), the description covers essential usage notes including side effects and re-usability constraints. It lacks details on return value, but output schema likely handles that. Mostly complete for a click tool.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds that target_id comes from the latest screen.observe and that button defaults left, but these are already in schema. No additional semantic value beyond schema.

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

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

The description clearly states the tool performs left/right/middle-click on a UIA target identified by an id from the latest screen.observe. It specifies the verb, resource, and source, and explicitly distinguishes it from the sibling tool input.click_xy by stating preference.

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

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

The description provides explicit guidance on when to use this tool over alternatives: 'Prefer over input.click_xy' and for click→type→keys sequences, use input.send_actions instead. It also advises not to reuse target_id after the screen may have changed, indicating when not to use it.

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

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

Beyond annotations (destructiveHint, openWorldHint), description adds 'Side effect: real mouse click on the remote desktop' and clarifies coordinate system usage.

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

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

Two focused sentences, no redundant words, front-loaded with core purpose and critical usage guidance.

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

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

Covers when to use, coordinate system, side effects, and alternatives; output schema handles return values; sufficient for a tool with good annotations.

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

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

Schema coverage is 100%, but description adds valuable context about native coordinates and their origin from screen.observe, enhancing schema meaning.

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

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

Clearly states 'Click at native screen coordinates' and distinguishes from sibling tool 'input.click_target' by specifying it's a last resort.

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

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

Explicitly says 'Last resort when no suitable UIA target exists — prefer input.click_target' and warns against using JPEG/downscaled pixel coords.

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

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

Discloses side effect of mouse_down → moves → mouse_up, and annotations include destructiveHint=true; no contradiction, and adds value 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.

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

Two sentences with zero fluff; purpose, use cases, side effect, and alternative are all front-loaded.

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

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

Covers purpose, usage, side effect, and alternative; output schema exists so return values need not be described. Could mention coordinate units but not necessary given schema bounds.

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

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

Schema coverage is 100%, so baseline 3; description adds no extra meaning beyond schema descriptions, which already adequately define each parameter.

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

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

Description clearly states 'Press-move-release mouse drag' as specific verb+resource, lists use cases (drawing, sliders, etc.), and distinguishes from input.send_actions.

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

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

Explicitly says when to use (drawing, sliders, selection boxes, drag-and-drop) and when to prefer alternative (input.send_actions for longer sequences).

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

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

Discloses side effect (scroll on element under point) and delta direction, adding context beyond annotations that already indicate destructive nature; could mention coordinate bounds but not critical.

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

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

Three sentences front-loading core action, then side effect, then guidance—no filler, every sentence informative.

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

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

Complete for a scroll tool with clear parameters and output schema; covers side effect, alternative tool, and post-action advice.

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

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

Schema descriptions already fully cover all 4 parameters; the description only restates delta sign meaning, adding minimal incremental value beyond the schema.

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

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

Clearly states action: move cursor then apply vertical mouse-wheel delta, with side effect on element under point. Distinguishes from sibling tools like input.click_xy, input.drag by specifying scroll and delta direction.

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

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

Explicitly advises preferring input.send_actions for multi-step sequences and recommends re-observing after scrolling before clicking, providing clear when-to-use 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.

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

Annotations already indicate destructiveHint, but the description adds details: all actions execute remotely, fails fast on invalid actions, observe_after defaults true, and observe_image behavior.

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

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

Concise at ~60 words, front-loaded with key info, every sentence adds value, and structured logically.

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

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

Given the multi-step complexity, schema coverage, annotations, and presence of output schema, the description fully addresses purpose, usage, parameters, and behavior.

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

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

Schema coverage is 100% with descriptions for all parameters. The description adds context beyond the schema, like click_target needing target_id from screen.observe and defaults for observe_after.

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

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

The description explicitly states it is a multi-step tool for running up to 10 predictable UI actions in one call, clearly distinguishing it from sibling tools like individual 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.

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

It provides explicit guidance: use for predictable actions, avoid batching across unpredictable waits, and prefer this over chaining solo tools.

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

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

Annotations already set destructiveHint=true and openWorldHint=true. The description adds a key behavioral trait: 'Side effect: real key events on the remote desktop.' While this is good context, it doesn't elaborate on the nature of the destruction (e.g., irreversible, system-level impact). Still, the side effect note provides meaningful transparency 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.

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

The description is extremely concise: three sentences that front-load the essential action and examples. Every sentence serves a distinct purpose (definition, side effect, usage guidance), with no wasted words. Ideal for quick agent comprehension.

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

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

Given the simplicity of the tool (2 parameters, no enums, output schema exists, sibling context clear), the description covers all needed aspects: purpose, side effect, and when to use alternatives. It leaves no gaps for an agent to misinterpret how or when to invoke this tool.

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

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

Schema coverage is 100% with descriptions for both parameters (keys and session_id). The description adds value by listing concrete examples for the keys parameter ('enter, tab, ctrl+s, alt+f4, win'), which helps the agent understand valid inputs. It does not add further detail to session_id, but the schema already suffices.

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

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

The description clearly states the verb 'Send' and the resource 'a key or chord to the focused window', with illustrative examples like 'enter, tab, ctrl+s'. It effectively distinguishes from siblings by naming alternatives (input.send_actions, input.type_text), making the tool's purpose unambiguous.

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

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

Explicit guidance is provided: 'Prefer bundling into input.send_actions when the shortcut follows a click/type in the same planned sequence. Use input.type_text for literal strings, not this tool.' This tells the agent when to use this tool versus alternatives, directly supporting correct selection.

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

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

Annotations already indicate openWorldHint and destructiveHint. The description adds context by mentioning 'Side effect: keystrokes on the remote desktop.' It does not contradict annotations and provides useful behavioral info beyond the schema.

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

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

The description is three sentences, front-loaded with the main purpose, and every sentence adds value: purpose, prerequisite, and alternative recommendation. No unnecessary words.

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

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

Given the tool's relative simplicity, the description covers the main function, prerequisites, side effects, and when to use alternatives. It does not mention error handling, but the output schema may cover return information. Overall, it provides sufficient context for agent selection.

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

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

Schema description coverage is 100%, and the description adds no new meaning beyond what the schema already provides for the two parameters. The description repeats that text is 'Literal text to type (not a key combo)' which matches the schema.

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

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

The description clearly states the action ('Type a Unicode string'), the target ('currently focused control'), and method ('via native input'). It distinguishes from siblings by noting it does not click first and recommending input.send_actions for form fills.

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

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

The description explicitly tells when to use this tool: after focusing the field, and when not to use it: for form fills, prefer input.send_actions. It also names specific alternatives (input.click_target, input.send_actions).

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

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

Beyond annotations (readOnlyHint, openWorldHint), the description adds 'Read-only — does not start a session', explains the USABLE flag condition, and describes the case when no rigs are usable. No contradictions.

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

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

Description is one focused paragraph with seven sentences, each adding value. It front-loads key fields and is efficient, though could be slightly more structured.

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

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

Despite no parameters, the description fully covers what the tool returns, how to interpret results, and actions to take when no usable rigs. The presence of an output schema reduces need to explain return values.

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

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

No parameters exist in the schema; schema coverage is 100%. The description does not need to add parameter info, but it implicitly uses the API key context. Baseline of 3 is appropriate.

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

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

The description clearly states it lists Windows machines (rigs) paired to the API key, specifies returned fields (id, name, online, api_access_enabled, USABLE flag), and distinguishes from siblings by noting it is read-only and must be called before start_session.

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

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

Explicitly says 'Call first before start_session', provides step-by-step instructions for handling no usable rigs (install agent, pair in Console, enable API access), and warns against asking for OS passwords.

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

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

Beyond readOnlyHint and openWorldHint annotations, the description adds key behaviors: no mouse/keyboard movement, target id validity, image suppression on changed=false. All disclosed clearly.

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

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

Front-loaded with purpose, then concise bullet-style guidance. Every sentence serves a purpose; no wasted words despite richness.

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

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

Given 5 parameters, 1 required, and existence of output schema, the description completely covers usage, parameter decisions, and behavioral constraints. No gaps.

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

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

With 100% schema coverage, the description still adds value: default values, when to enable image, approximate max_width/quality, and mark behavior. No redundancy.

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

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

The description clearly states 'Read the current screen' with a specific verb and resource, listing outputs (UIA targets, text summary) and distinguishing sibling tools like input.send_actions.

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

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

Explicit guidance: prefer input.send_actions for multi-step UI, observe after meaningful steps, when to set image=true, and how to handle the changed flag (do not re-analyze). No ambiguity.

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

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

Annotations provide destructiveHint and openWorldHint. Description adds specific side effects (stops billing, safety_restore, closes apps) and notes that subsequent operations on the 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.

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

Three sentences, front-loaded with purpose, then side effects, then usage guidance. No redundant or extraneous information.

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

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

For a tool with one parameter, annotations, and an output schema, the description is complete: it covers purpose, side effects, usage, and idempotency.

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

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

Schema coverage is 100%, so description need not add parameter semantics. Description does not elaborate on session_id beyond the schema, but this is acceptable.

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

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

Description explicitly states 'End an active session' with clear verb and resource. It distinguishes from siblings like session.start and session.status by noting that it closes apps and stops billing.

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

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

Explicitly states 'Always call when finished or abandoning — do not leave sessions open' and mentions idempotency and consequences of further use. Implicitly distinguishes from non-destructive siblings like session.status.

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

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

Adds beyond annotations by stating the tool is read-only for the agent and does not grant API key console access, plus the 60fps performance. No contradiction with annotations (readOnlyHint, openWorldHint). Could include error handling details.

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

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

Two sentences, no fluff. Front-loaded with main action and key details. Every word adds value.

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

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

With an output schema present, the return value is likely documented. Description covers what it returns (URL). Lacks mention of potential errors but sufficient for a simple tool with one required parameter.

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

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

Single parameter session_id is described in schema (100% coverage). Description does not add additional meaning or constraints beyond 'active session id'. Baseline maintained.

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

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

Clearly states it returns a console Live View URL at ~60fps for owner intervention. Distinct from sibling tools like session.status or screen.observe by providing a real-time interactive view.

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

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

Advises to offer on long or sensitive tasks and notes the owner must be signed into Glasswarp, which helps in deciding when to use. Does not explicitly compare to sibling tools but provides practical context.

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

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

Discloses side effects beyond annotations: 'begins wall-clock billing, shows an on-screen API session active indicator, enables observe/input until session.end' and idle auto-end after ~15 minutes. Adds value over destructiveHint and openWorldHint.

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

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

Four sentences, front-loaded with main action. Each sentence adds critical information (side effects, cleanup, idle timeout, destination details). No wasted words.

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

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

Given billing, idle timeout, and side effects, the description covers prerequisites (USABLE rig), outputs (session_id and Live View URL), and required follow-up (session.end). Well-suited for agent decision-making.

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

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

Schema has 100% coverage; the description reinforces 'from rigs.list' and 'USABLE rig' but adds no new parameter-specific details beyond what's in the schema.

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

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

The description clearly states 'Start a metered desktop session on a USABLE rig from rigs.list,' specifying the verb (start), resource (desktop session), and scope (from rigs.list). It distinguishes from sibling tools like session.end and session.live_view.

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

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

Provides explicit guidance: 'Always call session.end when done or abandoning' and 'Do not call if no USABLE rig exists.' Lacks explicit alternatives for read-only cases, but sibling tools cover that context.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description reinforces with 'Read-only — no input side effects' and lists specific metadata fields, adding value 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.

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

Two sentences, no wasted words. Front-loaded with key purpose and read-only nature, then specific use cases.

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

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

Given it has an output schema, low parameter count, and annotations cover safety, the description fully covers usage context. No gaps.

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

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

Schema coverage is 100% for the single parameter session_id, with adequate schema description. The tool description does not add new information about the parameter beyond what's in the schema.

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

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

The description clearly states the verb 'Fetch' and resource 'session metadata', listing specific fields. It distinguishes from siblings like session.start and session.end by emphasizing read-only status.

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

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

The description explicitly says when to use: 'to tell the user about metered time or confirm the session is still active before more actions.' It does not mention when not to use, but the context is clear enough.

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