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 action ('deletes or cancels') but doesn't clarify whether this is reversible, requires specific permissions, affects related resources, or has side effects like rate limits. This is a significant gap for a destructive operation.

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 appropriately sized and front-loaded, making it easy to parse 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?

For a destructive tool with no annotations, 0% schema coverage, and no output schema, the description is incomplete. It lacks critical details like behavioral traits, parameter meaning, and expected outcomes, leaving the agent with insufficient context 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?

The input schema has 1 parameter with 0% description coverage, so the description must compensate. It mentions 'a given task' but doesn't explain what taskId represents (e.g., format, source, or constraints), adding minimal value beyond the schema's basic structure.

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 ('deletes or cancels') and the target resource ('a given task'), which is specific and unambiguous. However, it doesn't differentiate this tool from its siblings (like runway_editVideo or runway_getTask), which would require a 5.

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 prerequisites (e.g., needing an existing task), exclusions, or sibling tools, leaving the agent to infer usage from context 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 describes what the tool does (edit video) and lists accepted ratios and reference image usage, but lacks critical behavioral details: it doesn't mention whether this is a read-only or destructive operation, expected processing time, rate limits, authentication needs, error handling, or output format. The description covers functional aspects but misses operational traits essential for an AI agent.

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 sized and front-loaded, starting with the core purpose. It efficiently lists parameter details without unnecessary fluff. However, the explanation of reference images is slightly verbose (e.g., the example with 'IMG_1'), which could be tightened. Overall, most sentences earn their place by clarifying parameters, but minor improvements in brevity are possible.

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 (video editing with 4 parameters), no annotations, and no output schema, the description is moderately complete. It covers parameter semantics well but lacks behavioral transparency and usage guidelines. For a tool with no structured safety or output information, it should provide more context on what the tool returns or potential side effects, leaving gaps that could hinder an AI agent's 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?

The description adds significant meaning beyond the input schema, which has 0% schema description coverage. It explains that 'promptText' is a prompt for the video, 'videoUri' accepts a URL or data URI, 'ratio' has specific accepted values with a default of 1280:720, and 'referenceImages' include tags that link to user prompts. This compensates fully for the schema's lack of descriptions, providing clear semantics for all 4 parameters.

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: 'Edit a video using Runway Aleph.' It specifies the action (edit), resource (video), and technology (Runway Aleph), which distinguishes it from sibling tools like runway_generateVideo (generation) or runway_upscaleVideo (enhancement). However, it doesn't explicitly contrast with all siblings, such as runway_cancelTask or runway_getTask, leaving some ambiguity.

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 mentions 'promptText' and 'videoUri' but doesn't explain scenarios where editing is preferred over generating a new video (runway_generateVideo) or upscaling (runway_upscaleVideo). There's no mention of prerequisites, constraints, or typical use cases, relying solely on parameter descriptions without contextual advice.

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 discloses key behavioral traits: the tool generates images, accepts reference images with tags, and returns a URL. However, it misses details like rate limits, authentication needs, or error handling. It does not contradict annotations (none provided).

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 sized and front-loaded, starting with the core purpose. Every sentence adds value (e.g., ratio options, reference image mechanics, return format). It could be slightly more structured but avoids redundancy and is 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 no annotations, no output schema, and 0% schema coverage, the description does well by explaining parameters and return values. However, for a generative tool with siblings, it lacks details on limitations (e.g., prompt length, image size) and error cases, leaving some gaps in 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. It adds significant meaning: it explains 'ratio' with available values and a default, and details 'referenceImages' with tags and usage examples. It covers all 3 parameters (promptText, ratio, referenceImages) beyond the schema, though not exhaustively for each.

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: 'Generate an image from a text prompt and optional reference images.' It specifies the verb ('generate'), resource ('image'), and distinguishes from siblings like runway_generateVideo (image vs. video generation) and runway_editVideo (generation vs. editing).

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 through examples (e.g., 'if the user prompt is "IMG_1 on a red background"') but does not explicitly state when to use this tool versus alternatives like runway_generateVideo or runway_upscaleVideo. It provides context for reference images but lacks clear when/when-not 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds valuable context beyond the schema: it specifies accepted ratios (e.g., 1280:720), default ratio (1280:720), allowed durations (5 or 10 seconds), and default duration (5 seconds). However, it does not mention other behavioral aspects like rate limits, authentication needs, or error handling, leaving some 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 sized and front-loaded: the first sentence states the core purpose, followed by specific constraints (ratios, durations) and usage guidelines. Every sentence adds essential information 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 complexity (video generation tool with 4 parameters), no annotations, and no output schema, the description is mostly complete. It covers purpose, constraints, defaults, and usage flow, but lacks details on output format, error cases, or authentication requirements, which could be important for an AI agent to use it correctly.

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 0%, so the description must compensate. It adds significant meaning beyond the schema: it explains that 'ratio' accepts specific values (e.g., 1280:720) and defaults to 1280:720, and 'duration' is either 5 or 10 seconds with a default of 5. This clarifies the semantics of two key parameters, though it does not detail 'promptImage' or 'promptText' beyond their 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 tool's purpose: 'Generate a video from an image and a text prompt.' It specifies the verb ('generate'), resource ('video'), and inputs ('image' and 'text prompt'), distinguishing it from siblings like runway_generateImage (which generates images) and runway_editVideo (which edits existing videos).

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: 'If the user asks to generate a video, always first use generateImage to generate an image first, then use the image to generate a video.' This clearly states when to use this tool (after generating an image) and references an alternative (runway_generateImage) for the prerequisite step.

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 it 'Returns details,' implying a read-only operation, but doesn't cover other traits like error handling, rate limits, authentication needs, or response format. This is a significant gap for a tool with zero 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 a single, efficient sentence that directly states the tool's purpose without waste. It's appropriately sized for a simple tool with no parameters, though it could be slightly more structured by front-loading key details more explicitly.

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 (0 parameters, no output schema), the description is minimal. However, it lacks completeness for an informational tool: it doesn't specify what 'details' include beyond examples, doesn't mention error cases or data format, and with no annotations, it fails to provide sufficient context for reliable 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?

The tool has 0 parameters, and schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately doesn't mention any. Baseline for 0 parameters is 4, as it avoids unnecessary 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?

The description clearly states the tool's purpose with a specific verb ('Returns') and resource ('details like credit balance, usage details, and organization information'), making it easy to understand what it does. However, it doesn't explicitly differentiate from sibling tools like 'runway_getTask' which might also retrieve information, so it doesn't reach the highest 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. It doesn't mention any context, prerequisites, or exclusions, such as when to choose this over 'runway_getTask' or other sibling tools, leaving the agent with minimal usage direction.

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 behaviors: the response varies by task status (e.g., 'url' for 'SUCCEEDED', 'error' for 'FAILED'), and it specifies retry timing (5 seconds for 'PENDING' or 'RUNNING'). This adds valuable context beyond basic input-output, though it could mention 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 appropriately sized and front-loaded, with three sentences that each add value: the first states the purpose, the second details response fields by status, and the third provides retry guidance. There is no wasted text, 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 moderate complexity (1 parameter, no output schema, no annotations), the description is fairly complete. It covers purpose, response behavior, and usage timing, but lacks details on parameter meaning, error cases beyond 'FAILED', or integration with sibling tools. This leaves minor gaps in full contextual understanding.

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 doesn't explicitly mention the 'taskId' parameter or its semantics, leaving it undocumented. However, the context implies the parameter is used to identify a task, providing minimal but insufficient detail for full understanding.

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: 'Get the details of a task.' It specifies the verb ('Get') and resource ('task'), making the function unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'runway_cancelTask' or 'runway_getOrg', 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 clear context on when to use this tool: to retrieve task details, with specific guidance on retrying for 'PENDING' or 'RUNNING' statuses. It implies usage for monitoring task progress but doesn't explicitly state when not to use it or name alternatives among siblings, such as for task cancellation or editing.

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 action ('upscale') but doesn't cover critical traits such as processing time, rate limits, authentication needs, output format, or potential side effects (e.g., file size changes). This leaves significant gaps in understanding how the tool behaves in practice.

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, with two sentences that directly address the tool's function and parameter usage without any wasted words. Each sentence earns its place by providing essential information efficiently, making it easy to scan 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 complexity (video processing), lack of annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't explain what the upscaled output looks like (e.g., resolution options, format), potential errors, or integration details, leaving too many unknowns for 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?

The description adds some meaning by explaining that 'videoUri' accepts 'a url of a video or a data uri of a video,' which clarifies the parameter's purpose beyond the schema's basic type. However, with 0% schema description coverage and only one parameter, this is adequate but minimal—it doesn't detail constraints like supported URL formats or video specifications, keeping it at the baseline.

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 ('upscale') and resource ('video'), and specifies the target outcome ('to a higher resolution'). It distinguishes from siblings like 'editVideo' or 'generateVideo' by focusing on resolution enhancement rather than editing or creation. However, it doesn't explicitly contrast with all siblings, keeping it at 4 instead of 5.

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 prerequisites (e.g., input video format requirements), when not to use it (e.g., for non-video files), or compare it to sibling tools like 'editVideo' for other modifications. This lack of contextual usage information results in a minimal score.

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