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 effectively describes key behavioral traits: it's a one-shot operation (not session-based), mentions payload size considerations, and explains the response_mode options including environment variable fallback. However, it doesn't cover potential errors, performance characteristics, or system requirements.

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 efficiently structured with zero waste. It begins with the core purpose, provides usage guidelines, then details parameters in a clear format. Every sentence adds value: the first establishes the tool's nature, the second provides critical usage guidance, and the parameter explanations are essential given the lack of schema descriptions.

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 5-parameter tool with no annotations and no output schema, the description does an excellent job covering purpose, usage, and parameters. However, it doesn't describe the return value format (though response_mode hints at it) or potential error conditions. Given the complexity and lack of structured documentation elsewhere, it's very complete but missing some edge case information.

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 0% schema description coverage, the description fully compensates by providing detailed semantic explanations for all 5 parameters. It explains what monitor_index values mean (0 for virtual desktop, 1..N for specific monitors), clarifies image_format options (png or jpeg), describes max_width behavior (resize while preserving aspect ratio), explains quality parameter applicability (JPEG only), and details response_mode options with their meanings and defaults.

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: 'Capture one screenshot in a single call.' It specifies the action (capture), resource (screenshot), and scope (one-shot). It distinguishes from siblings by explicitly mentioning the alternative session flow tools (start_screenshot_capture, get_screenshot_manifest, etc.).

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 versus alternatives: 'Prefer this tool for small/medium payloads when a one-shot response is desired. For larger payloads or robust transport, use the session flow...' It names specific alternative tools and clearly defines the use case boundaries.

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 effectively describes key behavioral traits: max duration enforcement, fixed capture rate, and output optimization for LLM temporal reasoning. However, it doesn't mention potential side effects like resource consumption or whether this is a read-only operation, leaving some gaps in behavioral 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 well-structured and appropriately sized. It starts with the core purpose, provides usage guidelines, lists behavioral constraints, and ends with output characteristics. Every sentence adds value with zero wasted words, making it highly efficient and front-loaded 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 (5 parameters, no annotations, but has output schema), the description is reasonably complete. It covers purpose, usage context, key behavioral constraints, and output characteristics. The existence of an output schema means return values don't need explanation. However, the lack of parameter semantics and some behavioral details (like side effects) prevents a perfect score.

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 by explaining parameters. It mentions 'duration_seconds' indirectly through 'Max duration' and 'capture rate' through 'TIMELINE_FPS', but doesn't explain the semantics of monitor_index, image_format, max_width, or quality parameters. This leaves most parameters undocumented, failing to compensate for the low schema coverage.

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

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

The description clearly states the tool's purpose: 'Capture a timeline in a single call' with a specific verb ('capture') and resource ('timeline'). It distinguishes from siblings by explicitly contrasting with the session flow tools (start_timeline_capture, get_timeline_manifest, etc.) for larger payloads, making the distinction clear and specific.

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 vs alternatives: 'Prefer this tool for short timelines when a one-shot JSON payload is acceptable. For larger timeline payloads or safer transport, use the session flow...' It names specific alternative tools and clearly defines the usage context, including exclusions for larger payloads.

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?

No annotations are provided, so the description carries the full burden. It discloses that the tool returns a base64 chunk and mentions concatenation, but doesn't cover critical behavioral aspects: it doesn't specify if this is a read-only operation, what permissions are needed, error handling (e.g., invalid indices), rate limits, or how chunk_base64 is structured. The description adds some context (chunk indexing and concatenation) but leaves significant gaps for a tool with no annotation coverage.

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 highly concise and front-loaded: the first sentence states the core purpose, and the second adds essential usage details. Every sentence earns its place by providing critical information without redundancy. It's appropriately sized for a tool with two parameters and clear functionality.

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 moderate complexity (fetching data chunks), no annotations, and an output schema (which likely covers return values), the description is reasonably complete. It explains the chunk-fetching process and indexing, but lacks details on error cases, authentication, or how total_chunks is determined. The output schema reduces the need to explain return values, but some behavioral context is still missing.

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 schema provides no parameter descriptions. The description adds meaning by explaining that chunk_index ranges from 0 to total_chunks-1, which clarifies its purpose and constraints. However, it doesn't describe capture_id (e.g., what it is, how to obtain it) or provide format details for either parameter. The description compensates partially but not fully for the low schema coverage.

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: 'Return one base64 chunk for a screenshot session' specifies the verb (return), resource (base64 chunk), and context (screenshot session). It distinguishes from siblings like get_screenshot_manifest (which likely returns metadata) and capture_screenshot (which initiates capture), but doesn't explicitly differentiate from get_timeline_chunk (a similar chunk-fetching tool for timelines).

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 stating 'Fetch chunks from `chunk_index=0` to `total_chunks-1`', suggesting it should be used iteratively across a range. However, it doesn't explicitly state when to use this tool versus alternatives like get_screenshot_manifest (which might provide total_chunks info) or how it relates to capture/release operations. The guidance is practical but lacks explicit exclusions or named 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it returns metadata and an ASCII preview, and it's used after capture initiation to discover chunk counts. However, it doesn't mention potential errors (e.g., invalid capture_id), rate limits, or authentication needs, leaving some behavioral aspects uncovered.

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 highly concise and well-structured with two sentences. The first sentence states the purpose, and the second provides usage guidelines. Every word earns its place, with no redundancy or fluff, making it easy to parse and understand quickly.

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 moderate complexity (1 parameter, no annotations, but with an output schema), the description is complete enough. It explains the purpose, usage sequence, and key outputs (metadata, ASCII preview, total_chunks discovery). Since an output schema exists, the description doesn't need to detail return values, and it adequately covers the tool's role in the workflow with sibling tools.

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% description coverage for its single parameter 'capture_id'. The description compensates by implicitly explaining the parameter's role: it refers to 'after `start_screenshot_capture`', indicating capture_id likely comes from that previous step. This adds meaningful context beyond the bare schema, though it doesn't specify format or constraints explicitly.

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: 'Return screenshot session metadata and an ASCII preview.' It specifies both the resource (screenshot session) and the output (metadata + preview), distinguishing it from siblings like 'get_screenshot_chunk' or 'capture_screenshot' by focusing on manifest retrieval rather than chunk data or capture initiation.

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 usage guidance: 'Use this as step 2 after `start_screenshot_capture` to discover `total_chunks` and preview content.' It specifies the exact sequence (after start_screenshot_capture) and purpose (discover total_chunks and preview), clearly differentiating when to use this tool versus alternatives like 'get_screenshot_chunk' for actual data retrieval.

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 effectively describes the chunk-fetching behavior and reconstruction process, but lacks details on error handling, rate limits, or authentication needs. It doesn't contradict any annotations, but could be more comprehensive for a tool with no annotation support.

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 perfectly front-loaded with the core purpose in the first sentence, followed by essential usage instructions. Every sentence earns its place by providing critical guidance without any wasted words or 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 the tool's moderate complexity (chunked data retrieval), no annotations, and the presence of an output schema (which handles return values), the description is largely complete. It covers purpose, sequencing, and reconstruction, though could benefit from mentioning error cases or performance considerations.

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 has 0% description coverage for its 2 parameters, so the description must compensate. It explains that chunk_index should range from '0 to total_chunks-1' and that timeline_id identifies a session, adding crucial context beyond the bare schema. However, it doesn't specify the format or constraints for timeline_id.

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 specific action ('Return one JSON text chunk') and resource ('for a timeline session'), distinguishing it from siblings like get_timeline_manifest (which provides metadata) and get_screenshot_chunk (which handles screenshots). It precisely defines the tool's role in fetching data chunks.

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 states when to use this tool ('Use this after get_timeline_manifest') and provides clear sequencing instructions ('fetch chunks from chunk_index=0 to total_chunks-1 in order'). It distinguishes usage from the manifest-fetching sibling and implies alternatives for non-chunk operations.

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?

No annotations are provided, so the description carries the full burden. It discloses that the tool returns metadata (not full payload) and is used for discovery and validation, which adds useful context. However, it lacks details on behavioral traits such as error handling, performance, or side effects, leaving gaps for a tool with no annotation coverage.

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 front-loaded with the core purpose in the first sentence, followed by usage guidelines in the second. Both sentences earn their place by adding value beyond structured fields, with zero wasted words, making it highly efficient and well-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?

Given the tool's moderate complexity (1 parameter, no annotations, but with an output schema), the description is mostly complete. It explains the purpose, usage, and workflow role adequately. However, it could improve by addressing potential errors or the format of returned metadata, though the output schema mitigates some of this need.

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 1 parameter with 0% description coverage, so the description must compensate. It implies the parameter 'timeline_id' is required (as per the schema) by referencing it in the workflow context ('after `start_timeline_capture`'), but does not explicitly explain its semantics or format. Since there is only 1 parameter, the baseline is 4, but it could be higher with more detail.

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 specific action ('Return timeline session metadata') and resource ('timeline session'), distinguishing it from siblings like 'get_timeline_chunk' (which retrieves payload data) and 'get_screenshot_manifest' (which handles screenshots). It explicitly mentions what it does not return ('without the full payload'), enhancing differentiation.

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: 'Use this as step 2 after `start_timeline_capture`'. It also specifies the purpose ('to discover `total_chunks` and validate integrity metadata'), clearly indicating its role in a workflow and distinguishing it from alternatives like 'capture_timeline' or 'list_monitors'.

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 effectively explains the return format by describing what monitor indices mean (index=0 is virtual full desktop, index>=1 targets specific monitors), which is valuable behavioral context for how to interpret the output.

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 perfectly structured with two sentences: the first states the purpose, the second provides usage guidance and output interpretation. Every word earns its place with zero waste or 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 the tool has 0 parameters, 100% schema coverage, and an output schema exists, the description provides exactly what's needed: clear purpose, usage guidance, and interpretation of the output values. It doesn't need to explain return values since an output schema exists.

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 0 parameters with 100% schema description coverage, so the baseline would be 4. The description appropriately doesn't discuss parameters since there are none, and instead focuses on explaining the output semantics.

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 as 'List available monitors' which is a specific verb+resource combination. However, it doesn't explicitly distinguish this from its sibling tools (like capture_screenshot or get_screenshot_manifest) beyond the general domain of monitor operations.

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: 'Use this first when the caller does not know which monitor index to target.' This clearly establishes the primary use case and distinguishes it from tools that require a specific monitor index.

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?

No annotations are provided, so the description carries the full burden. It discloses that this tool frees memory and should be called after reading chunks, which are useful behavioral traits. However, it lacks details on permissions, side effects (e.g., if the session becomes inaccessible), or error handling, leaving 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 very concise with two sentences that are front-loaded and waste no words. Each sentence adds value: the first states the purpose, and the second provides 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?

Given the tool has an output schema (which likely covers return values) and no annotations, the description is moderately complete. It covers purpose and usage but lacks details on parameters, error cases, or dependencies with siblings like 'get_screenshot_chunk', leaving room for improvement in context.

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 implies 'capture_id' is needed to identify the session but doesn't explain its format or source. The description adds minimal context beyond the schema, resulting in a baseline score due to incomplete parameter documentation.

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 ('Release') and resource ('screenshot session'), and mentions freeing memory as the outcome. It distinguishes from siblings like 'capture_screenshot' or 'start_screenshot_capture' by focusing on cleanup, but could be more explicit about what a 'screenshot session' entails.

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 on when to use this tool ('after reading all required chunks'), which helps differentiate it from siblings like 'get_screenshot_chunk'. However, it doesn't specify alternatives or when not to use it, such as if chunks are still needed.

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?

No annotations are provided, so the description carries the full burden. It mentions 'free memory', which hints at resource management, but doesn't disclose critical behavioral traits like whether this is destructive (likely yes, given 'release'), error conditions, or performance implications. The description is too brief to cover necessary details for a tool that likely modifies state.

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 are front-loaded and waste no words. Every sentence adds value: the first states the action, and the second provides usage timing.

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 likely involves resource management (freeing memory) and has an output schema (which reduces the need to describe returns), the description is minimal but covers the basic action and timing. However, for a tool with no annotations and 0% schema coverage, it should do more to explain behavioral aspects and parameter details to be fully complete.

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 doesn't add any meaning to the 'timeline_id' parameter beyond what the schema provides (a required string). With 0% coverage and 1 parameter, the baseline is 4, but since the description fails to explain what 'timeline_id' is or its format, it doesn't fully compensate, warranting a lower 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 with a specific verb ('release') and resource ('timeline session'), and distinguishes it from siblings like 'release_screenshot_capture'. However, it doesn't fully differentiate from 'release_screenshot_capture' beyond the resource type, and 'free memory' is somewhat vague.

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 context on when to use it ('after reading all required chunks'), which implies it should follow chunk retrieval operations. It doesn't explicitly state when not to use it or name alternatives, but the context is sufficient for basic 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?

No annotations are provided, so the description carries the full burden. It discloses that the screenshot is stored 'in a temporary server-side session' and implies a multi-step process, but lacks details on permissions, rate limits, error handling, or what 'temporary' entails. It adds some context but is incomplete for a tool with no 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 front-loaded with the core purpose in the first sentence, followed by concise usage guidelines. Both sentences earn their place by providing essential workflow context without redundancy, making it efficient and well-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?

Given the tool's complexity (multi-step flow, 5 parameters with 0% schema coverage, no annotations), the description is incomplete. It explains the workflow well but omits parameter details and behavioral aspects like session management. The presence of an output schema helps, but gaps remain for adequate 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 for the 5 undocumented parameters. However, it provides no information about any parameters (e.g., what 'monitor_index' or 'chunk_size' mean), failing to add meaning beyond the bare schema. This leaves parameters largely unexplained.

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 specific action ('Capture a screenshot') and resource ('store it in a temporary server-side session'), distinguishing it from siblings like 'capture_screenshot' by specifying it's part of a chunked flow. The purpose is explicit and well-defined.

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 states when to use this tool ('step 1 of the chunked screenshot flow') and provides a clear sequence of next steps ('get_screenshot_manifest', 'get_screenshot_chunk', 'release_screenshot_capture'), differentiating it from alternatives like 'capture_screenshot' by outlining the workflow.

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 describes the tool's role in a multi-step flow and mentions temporary storage, which adds useful context. However, it lacks details on permissions, rate limits, error conditions, or what 'temporary' means (duration, cleanup). For a tool with 6 parameters and no annotations, this is a moderate gap.

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 highly concise and well-structured: two sentences that front-load the purpose and follow with specific usage steps. Every sentence earns its place by providing essential guidance without redundancy or fluff.

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 (6 parameters, no annotations, but with an output schema), the description is partially complete. It explains the workflow and purpose well, but lacks parameter explanations and behavioral details. The output schema may cover return values, but for a tool initiating a capture process, more context on parameters and behavior would improve completeness.

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. The description mentions 'chunked session' which hints at 'chunk_size', but does not explain any of the 6 parameters (e.g., 'duration_seconds', 'monitor_index', 'image_format'). It fails to add meaningful semantics beyond what the bare schema provides, leaving parameters largely unexplained.

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: 'Capture a timeline and store it in a temporary chunked session.' This specifies the verb ('capture'), resource ('timeline'), and storage mechanism ('temporary chunked session'). It distinguishes from siblings like 'capture_timeline' by emphasizing the chunked session aspect, though not explicitly contrasting with 'capture_screenshot' or 'start_screenshot_capture'.

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 usage guidelines: 'Use this as step 1 of the chunked timeline flow. Next calls should be: `get_timeline_manifest`, then all `get_timeline_chunk`, then `release_timeline_capture`.' This clearly states when to use it (step 1 of a specific flow) and what alternatives to use next, distinguishing it from other capture tools by outlining a sequential process.

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