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

Annotations already mark it as read-only and non-destructive. The description adds useful behavioral detail by specifying that it returns status, version, and installation instructions if missing, making the tool's output behavior transparent.

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, focused sentence that states the action and expected output. It avoids redundancy with the schema and annotations.

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 zero-parameter check tool with read-only annotations, the description fully covers functionality and return values. It is complete enough for an agent to invoke and interpret the result.

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, so the baseline score is 4. The description correctly focuses on behavior rather than parameters, and no additional parameter context is needed.

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 function: checking if yt-dlp is installed and available in PATH. It also specifies return values (status, version, installation instructions). This distinguishes it from sibling video tools like download_video and get_video_info.

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 the tool is for dependency checking but does not explicitly state when to use it relative to siblings. It lacks guidance on using it before downloads or as a prerequisite, but the name and context make the intended usage fairly clear.

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 readOnlyHint=false and destructiveHint=false, so the description does not need to repeat that. It adds that the tool uses yt-dlp and returns a path, which is useful. However, it does not disclose behaviors like overwriting files, creating directories, or network dependencies, so some transparency gaps remain.

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 long, with no fluff. It front-loads the main purpose, then states the return value and underlying library. 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?

Given the simple tool, the description covers essentials: what it does, what it returns, and how it works. The schema covers parameter defaults, and annotations indicate side effects. It does not mention potential errors or the need for check_dependencies, but these are not critical for a basic download 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%: each parameter has a meaningful description (e.g., url is any yt-dlp supported URL, filename defaults to video title, output_dir defaults to system temp). The tool description itself adds no additional parameter semantics, so baseline 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 the tool's purpose: 'Download only the audio from a URL as MP3.' This is a specific verb+resource combination that distinguishes it from the sibling tool download_video. It also mentions the output (path to downloaded file), making the 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?

The description provides clear context: this tool is for downloading audio only, implying it should be used when audio is needed. It does not explicitly mention alternatives or exclusions, but the phrase 'Download only the audio' and the sibling context (download_video) imply a usage boundary.

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 readOnly=false (write), openWorld=true (external interaction), and destructive=false. The description adds 'Uses yt-dlp with best quality mp4 format' and return path, but does not disclose behavior around file overwrites, failure modes, or network reliability. This provides some context beyond annotations but not rich detail, so a mid-range score is appropriate.

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 concise sentences, each delivering essential information: purpose, return value, and implementation detail. No fluff, front-loaded with the primary action, and all sentences earn their place. This is an example of efficient, well-structured description.

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 no output schema, the description appropriately covers the return value (path). The underlying tool (yt-dlp) and format are disclosed. The presence of sibling tool check_dependencies hints at prerequisites, but the description could be slightly more explicit about failure cases or dependency requirements. Overall, it is complete for a simple download tool given the rich schema and 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 description coverage is 100%, with each parameter (url, filename, output_dir) already documented clearly. The description does not add parameter-level details, but it does note 'best quality mp4 format', which implies the output format despite no format parameter. Given the high schema coverage, a baseline score 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 the action ('Download a video from a URL to a local file') and the return value ('Returns the path'), distinguishing it from sibling tools like download_audio (audio-specific), get_video_info (metadata-only), and check_dependencies (environment check). The verb+resource construction is explicit and 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?

The usage context is implied by the tool's name and description (use for downloading videos), but there is no explicit guidance on when to choose this over download_audio or get_video_info, nor any mention of prerequisites like network access or yt-dlp installation. This is adequate but lacks exclusions or alternative recommendations.

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 read-only and non-destructive behavior. The description adds useful context by mentioning the use of yt-dlp --dump-json and listing metadata fields returned. It does not detail network behavior or error handling, but the added implementation detail and output field list provide value beyond the 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 a single sentence that front-loads the purpose and lists output fields without unnecessary words. Every element serves a clear function.

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 simple single-parameter tool, no output schema, and strong annotations, the description sufficiently covers the return values by listing metadata fields. It is complete enough for an agent to understand what information will be provided and how to invoke the tool 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?

Schema coverage is 100% with a detailed description of the url parameter ('YouTube, Vimeo, or any yt-dlp supported URL'). The tool description only says 'video URL' and adds no new meaning beyond what the schema already provides, so the baseline 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 gets metadata about a video URL and lists specific fields (title, duration, resolution, fps, filesize, thumbnail, description). This distinguishes it from sibling tools like download_video and download_audio, which focus on downloading rather than metadata retrieval.

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 purpose of 'get metadata' is clearly distinct from downloading, implying usage when metadata is needed rather than actual content. However, it does not explicitly state when to use this tool instead of alternatives, so it lacks explicit exclusion guidance but provides clear context.

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