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

With no annotations provided, the description carries full burden but offers minimal behavioral insight. It mentions the output includes 'bounds and pixel sizes', which hints at return format, but doesn't disclose whether this is a read-only operation, potential side effects, or performance characteristics. For a tool with zero annotation coverage, this is inadequate.

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

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

The description is a single, efficient sentence that front-loads the core action ('List available displays') and adds specific detail ('with bounds and pixel sizes'). There is zero wasted verbiage, making it highly concise and well-structured for quick 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 tool's simplicity (no parameters, no output schema), the description is minimally adequate. It states what the tool does and hints at output content, but lacks guidance on usage versus siblings and behavioral details. For a zero-parameter tool, this is acceptable but not comprehensive.

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

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

The tool has zero parameters, and schema description coverage is 100% (though trivial). The description doesn't need to compensate for missing parameter documentation. A baseline of 4 is appropriate as there are no parameters to explain beyond what the empty schema already indicates.

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 ('List') and resource ('available displays'), specifying what information is included ('with bounds and pixel sizes'). It distinguishes from siblings like 'list_windows' by focusing on displays rather than windows. However, it doesn't explicitly contrast with 'screenshot_display' which also operates on displays.

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

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

No guidance is provided on when to use this tool versus alternatives. The description doesn't mention when to choose 'list_displays' over 'list_windows' or 'screenshot_display', nor does it specify prerequisites or context for usage. The agent must infer usage from tool names alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool lists windows but doesn't describe return format (e.g., array of objects), pagination, rate limits, permissions needed, or whether it's a real-time snapshot versus cached data. This leaves significant gaps for a tool with potential complexity.

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

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

The description is a single, efficient sentence that front-loads the core action ('List on-screen windows') and adds essential details ('with bounds and owner metadata'). There's zero waste or redundancy, making it appropriately sized for its purpose.

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

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

Given no annotations and no output schema, the description is incomplete for a tool that likely returns structured data about windows. It lacks details on return format, error handling, or behavioral traits like whether it requires screen recording permissions. For a tool in a context with sibling recording/screenshot tools, more completeness is needed.

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

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

The input schema has 0 parameters with 100% coverage, so the schema fully documents the absence of inputs. The description doesn't add parameter details (none exist), but it implies the tool operates without filters, which aligns with the schema. Baseline is 4 for zero-parameter tools when schema coverage is complete.

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 ('List') and resource ('on-screen windows'), specifying what information is returned ('bounds and owner metadata'). However, it doesn't explicitly differentiate from sibling tools like 'list_displays' or 'screenshot_window', which prevents a perfect score.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'list_displays' for displays or 'screenshot_window' for capturing window images. There's no mention of prerequisites, timing considerations, or exclusion criteria, leaving usage context implied at best.

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?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions default values (fps defaults to 10) and clarifies what 'system_audio' does, but doesn't cover critical aspects like: whether recording starts immediately, what happens if the window closes mid-recording, file size considerations, permission requirements, or error conditions. For a recording tool with zero annotation coverage, this leaves significant behavioral gaps.

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 appropriately concise with two sentences that efficiently convey core functionality and parameter details. The first sentence states the main purpose, and the second provides specific parameter information. There's no wasted verbiage, though it could be slightly more structured with clearer separation between purpose and parameter 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?

For a recording tool with 5 parameters, 0% schema description coverage, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns, how to handle errors, what the MP4 quality/encoding is, or provide usage examples. The description covers basic functionality but leaves too many contextual gaps for effective agent use.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaningful context for two parameters: explaining that 'fps defaults to 10' and clarifying that 'system_audio records global system audio.' However, it doesn't address the other three parameters (window_id, duration_seconds, output_path), leaving their purpose and format undocumented. The partial compensation earns a baseline score.

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

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

The description clearly states the tool's purpose: 'Record a window for a fixed duration (seconds) to an MP4.' This specifies the verb (record), resource (window), and output format (MP4). However, it doesn't explicitly differentiate from sibling tools like 'record_window_start' and 'record_window_stop', which appear to be related recording tools with different control mechanisms.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'record_window_start/stop' for continuous recording or 'screenshot_window' for single captures. There's no context about prerequisites, limitations, or appropriate use cases beyond the basic functionality.

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?

With no annotations provided, the description carries the full burden. It mentions that recording continues until stopped and includes default values for 'fps' and 'system_audio', but fails to disclose critical behavioral traits such as permissions needed, file format, error handling, or resource usage. This leaves significant gaps for a tool that likely involves system-level operations.

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 two sentences that directly address key aspects: the tool's action and default parameter values. Every sentence adds value without redundancy, making it front-loaded and efficient.

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

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

Given the complexity of a recording tool with no annotations, no output schema, and 4 parameters (only 2 partially explained), the description is incomplete. It lacks details on output format, error conditions, prerequisites, and full parameter semantics, which are essential for safe and effective use.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaning for 'fps' (defaults to 10) and 'system_audio' (records global system audio), covering 2 of 4 parameters. However, it doesn't explain 'window_id' or 'output_path', leaving half the parameters without semantic context 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?

The description clearly states the action ('Start recording a window') and specifies it continues 'until record_window_stop is called', which distinguishes it from the sibling tool 'record_window_duration'. However, it doesn't explicitly contrast with all siblings like 'screenshot_window'.

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

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

The description implies usage by mentioning the dependency on 'record_window_stop' and default values, but doesn't explicitly state when to use this tool versus alternatives like 'record_window_duration' or 'screenshot_window'. It provides some context but lacks clear exclusions or comparisons.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool stops a recording, implying a mutation action, but lacks details on permissions, side effects (e.g., whether the recording is saved or discarded), error handling, or response format. This leaves significant gaps for a mutation tool.

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

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

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and wastes no space, making it highly concise and well-structured for quick understanding.

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 complexity as a mutation operation with no annotations, no output schema, and low schema coverage, the description is incomplete. It lacks crucial details like behavioral traits, parameter explanations, and expected outcomes, making it inadequate for safe and effective use by an AI agent.

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

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

Schema description coverage is 0%, so the description must compensate for the undocumented parameter. It mentions 'recording_id' indirectly by referencing record_window_start, but provides no explicit explanation of the parameter's meaning, format, or how to obtain it, failing to add sufficient value beyond the bare 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 ('Stop a recording') and references the specific resource ('recording started with record_window_start'), making the purpose unambiguous. It distinguishes from siblings like record_window_start by indicating it's the complementary stop operation, though it doesn't explicitly differentiate from other recording-related tools like record_window_duration.

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

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

The description implies usage by referencing record_window_start as the prerequisite, suggesting this tool should be used after starting a recording. However, it provides no explicit guidance on when not to use it or alternatives among siblings like record_window_duration, leaving some ambiguity in 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It states the tool captures an image but doesn't mention whether this requires permissions, affects system performance, has rate limits, or what happens on failure. The description doesn't specify if the capture is instantaneous or has delays, or where the output is saved (only that 'output_path' is a parameter). This leaves significant behavioral gaps for a tool that interacts with system displays.

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

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

The description is a single, efficient sentence that gets straight to the point with zero wasted words. It's appropriately sized for a simple capture tool and front-loads the core functionality. Every word earns its place by specifying the action, output format, and target.

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 2 parameters, 0% schema coverage, no annotations, and no output schema, the description is insufficient. It doesn't explain parameter semantics, behavioral implications, or relationship to sibling tools. While concise, it lacks the contextual information needed for an agent to use this tool effectively, especially given the complexity of interacting with system displays.

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

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

Schema description coverage is 0%, so the description must compensate for undocumented parameters. It mentions 'display_id' but doesn't explain what valid values are or how to obtain them. It doesn't mention 'output_path' at all, leaving this parameter completely unexplained. The description adds minimal semantic value beyond what the parameter names themselves imply.

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 ('Capture') and the resource ('PNG/JPG of a display by display_id'), making the purpose immediately understandable. It doesn't explicitly differentiate from sibling tools like 'screenshot_window', but the focus on 'display' rather than 'window' provides some implicit distinction. The description avoids tautology by specifying the output format and target.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'screenshot_window' or other recording tools. It mentions the 'display_id' parameter but doesn't explain how to obtain valid IDs (e.g., from 'list_displays') or when this tool is appropriate versus window-based capture. No exclusions or prerequisites are mentioned.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool captures an image but doesn't mention file system effects (e.g., that 'output_path' saves a file), permissions needed, potential side effects, or error conditions. For a tool that writes files, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence with zero waste. It's appropriately sized for a simple tool and front-loads the core functionality. Every word earns its place without redundancy.

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 no annotations, 0% schema coverage, no output schema, and a tool that performs file system writes, the description is incomplete. It doesn't cover parameter meanings, behavioral traits, or output details. For a tool with two parameters and significant implications (saving files), this is inadequate.

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

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

Schema description coverage is 0%, so the description must compensate. It mentions 'window_id' but doesn't explain its format or how to obtain it. It doesn't mention 'output_path' at all, leaving a required parameter undocumented. The description adds minimal value beyond the schema's parameter names.

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 ('Capture') and resource ('a PNG/JPG of a window'), specifying the required parameter ('by window_id'). It distinguishes from 'screenshot_display' by focusing on windows rather than displays. However, it doesn't fully differentiate from other window-related tools like 'record_window_duration' beyond the capture action.

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

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

No explicit guidance on when to use this tool versus alternatives is provided. The description implies usage when needing a screenshot of a specific window, but doesn't mention prerequisites (e.g., needing 'list_windows' first to get window_id) or when to choose 'screenshot_display' instead. This leaves the agent with minimal context for decision-making.

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