Boost.Audio

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

The description discloses the output format ('Returns a downloadable WAV audio file'), which is not covered by the annotations or schema. It also confirms the generative nature without contradiction. However, it adds limited detail about failure modes, rate limits, or authentication, which the annotations don't cover; still, the output disclosure exceeds the baseline.

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 compact and front-loaded with the primary action, followed by clear use cases and a final output note. Every sentence provides relevant information 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 the absence of an output schema and the tool's moderate complexity, the description sufficiently covers the core purpose, usage scenarios, and return format. It does not repeat tier limitations or internal flags, but those are well-documented in the input schema. The description is complete enough for an agent to select and 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?

All six parameters have detailed schema descriptions covering 100% coverage, including defaults, enums, and constraints. The tool description repeats 'Supports 23 languages' and 'Adjust voice expression' but adds no additional parameter semantics beyond the schema. Thus, it earns the baseline of 3.

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 opens with 'Generate natural speech from text using Boost Audio AI,' clearly stating the tool's function as a text-to-speech generator. It also mentions language support and voice expression adjustment, and the use cases distinguish it from sibling audio editing tools.

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

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

The description explicitly states 'Use this when the user wants to convert text to audio, create a voiceover, narrate content, or listen to text read aloud,' providing clear when-to-use context. However, it does not mention exclusions or alternatives, so it stops short of full comparative guidance.

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

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

Annotations already communicate non-read-only and non-destructive behavior. The description adds no extra behavioral context beyond the core detection purpose—e.g., no details on output format, limitations, or side effects. It is adequate but not enhancing beyond annotations.

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

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

The description is two sentences, front-loaded with the primary action and use case. Every sentence earns its place with no filler 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?

The tool has 5 parameters, 0 required, and no output schema. The description explains purpose and usage context, and the schema covers parameter meanings. However, because the output schema is absent, the description could have mentioned the return format (e.g., BPM as number, key as string) to improve completeness, but the title and purpose make this largely implicit.

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

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

Schema coverage is 100%, so each parameter is already documented. The description itself does not add semantic detail about parameters, matching the baseline for high schema coverage. It doesn't clarify when to prefer audio_url vs audio_base64 vs file_token beyond what the schema states.

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 detects BPM and musical key of an audio file with a specific verb ('Detect') and resource. It also explicitly lists the use cases ('tempo, key, scale or harmonic information'), distinguishing it from sibling tools that convert, trim, or split audio.

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 when the user asks for the tempo, key, scale or harmonic information of a song.' However, it does not mention when not to use it or refer to alternative tools for other audio analysis tasks, so it falls short of a 5 by the rubric.

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

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

Annotations already declare readOnlyHint=false and destructiveHint=false. The description adds no extra behavioral context beyond stating the conversion action, such as output details or large-file handling. It does not contradict annotations.

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

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

Two concise sentences: the first states the core function, the second gives usage guidance. No wasted words, information is front-loaded.

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

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

All six parameters are optional and the schema provides thorough descriptions, handling input ambiguity. The description covers the primary use case but omits what the output looks like; however, this is a minor gap given the schema richness and no output schema requirement.

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 having a clear description. The tool description adds no parameter-level meaning, so the baseline of 3 applies.

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 converts audio files between specific formats (MP3, WAV, FLAC, OGG, M4A) with explicit examples. This distinguishes it from sibling tools like stem_splitter or vocal_remover.

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

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

The description explicitly says 'Use this when the user wants to change the format of an audio file', providing clear context. It does not name alternatives or state when not to use it, but the purpose is narrow enough that the guidance is effective.

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?

The description adds the supported input video containers and output audio formats, which are not in the annotations. It also states the result is a download, but does not describe the response format (e.g., direct file link, JSON with URL) or any processing side effects. Annotations already convey read-only/non-destructive nature, so the description adds moderate but not rich context.

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: two sentences with no filler. The first sentence states the action and formats, the second provides usage guidance. All information is front-loaded and every word contributes to the tool's utility.

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 there is no output schema, the description should explain what the tool returns. It says 'download as MP3 or WAV,' implying a downloadable artifact, but doesn't clarify the response structure (e.g., binary payload, URL, or file token). For a tool with 6 parameters and multiple upload methods, the description covers the core action but leaves output expectations ambiguous.

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

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

Schema descriptions already cover all 6 parameters with 100% coverage, so the baseline is 3. The description adds value by specifying accepted video formats (MP4, MOV, WebM, M4V), which is not in the schema, and by clarifying target_format as the output selection (MP3/WAV). This extra context improves agent comprehension beyond the schema alone.

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 extracts audio from video files (MP4, MOV, WebM, M4V) and converts to MP3 or WAV. The verb 'Extract' and resource 'audio track' make the purpose unambiguous, and it distinguishes itself from sibling audio tools like converter or trimmer by focusing on video sources.

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 second sentence explicitly says 'Use this when the user wants to get audio out of a video file,' providing clear context for when to select this tool. However, it does not mention when not to use it or name alternative tools, so it lacks the full exclusions/alternatives guidance seen in the highest-calibration examples.

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 annotations (readOnlyHint=false) indicating a mutating operation, the description adds that it returns a mix and optionally separated stems. However, it omits the asynchronous job workflow (start/poll) and does not disclose that generation takes time or requires polling, which is important behavioral context not conveyed by 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 three sentences, each earning its place: the first states the core action, the second describes the return value, and the third gives usage context. There is no 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?

Despite the rich schema and annotations, the description does not explain the multi-step workflow involving `_action='start'`, `_action='poll'`, and internal secrets. While the schema covers these details, the description alone would not fully guide an agent on how to correctly invoke this tool for a generation task, especially without an output schema.

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 covers 100% of parameters with detailed descriptions, so the baseline is 3. The description does not add additional parameter meaning except implicitly referencing 'text prompt' which maps to the `prompt` parameter, but this is also clearly described in the schema.

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

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

The description clearly states the tool generates a full audio track from a text prompt, which is a specific verb+resource. It also distinguishes from siblings by explicitly mentioning AI-generated music, instrumentals, songs with lyrics, and demos, which are capabilities unique to this generation tool.

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 when-to-use guidance: 'Use this when the user wants AI-generated music, an instrumental, a song with lyrics or a quick demo from an idea.' It gives explicit context but does not mention exclusions or alternative tools, so it falls short of a 5.

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 annotations already indicating readOnlyHint=false and destructiveHint=false, the description adds valuable context about plan requirements ('Ultimate plan unlocks a 6-stem mode') and the difference in output stems. No contradiction with annotations. It does not detail all side effects (e.g., upload limits, processing time), but adds sufficient behavior beyond annotations.

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

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

Two sentences, front-loaded with the core action and outputs. Every clause is relevant, including the plan note and usage hint. No redundant filler.

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?

No output schema exists, but the description implies the result (separate stems) by stating the purpose. It covers the main workflow and mentions the plan limitation. Lacks explicit details on how results are delivered, but is adequate for a moderately complex tool with rich input schema descriptions.

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

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

Schema description coverage is 100%, so baseline is 3. The description enriches the 'mode' parameter by explaining what 4-stem vs 6-stem yields ('separate guitar and piano'), which is not fully captured in the schema's enum description. This adds practical meaning.

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

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

The description uses a specific verb 'Split' and clearly identifies the resource ('a song into separate stems') with explicit outputs (vocals, drums, bass, other). It also distinguishes from sibling tools by stating 'Use this when the user wants individual instrument stems.'

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

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

Provides clear context for when to use the tool: 'Use this when the user wants individual instrument stems.' It does not explicitly mention alternatives or exclusions, but the context is specific and actionable.

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?

It discloses the interactive flow (asks 4 questions), output shape (3 tiers with hardware per slot), and localization/UTM behavior, all of which are valuable beyond the minimal annotations. It does not detail OAuth/save side effects, but there is no contradiction with 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 well-structured: main behavior first, then use cases, then a highlighted locale requirement. It is slightly redundant with the schema (hardware slot list, category examples), which prevents a perfect score, but it remains compact and readable.

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 15 parameters and no output schema, the description covers the primary build flow and return structure well (3 proposals, hardware slots, links). It does not elaborate on search/save action outputs, but those are partially documented in the parameter descriptions.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful semantics: locale must be inferred from chat language, budget is distributed by purpose, and purchase links use UTM tracking. This goes beyond the raw schema and helps the agent invoke actions correctly.

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 opens with a specific verb and resource: 'Open Soundra-style studio wizard' that 'builds 3 studio proposals' with hardware slots and purchase links. It clearly distinguishes this from the sibling audio-processing tools by focusing on studio setup recommendations rather than audio manipulation.

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 gives explicit use cases: 'when the user asks to recommend studio gear, plan a home studio for X PLN/EUR, swap a device, or compare price tiers.' It does not explicitly mention when not to use it or name alternatives, but the use-case list is clear enough for an agent to route correctly.

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 disclose readOnlyHint=false and destructiveHint=false, and the description adds that a downloadable MIDI file is produced. However, it does not explain processing time, limitations, or upload requirements, which are left to the schema. This is adequate but not rich.

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 two sentences long, front-loaded with the primary purpose, and has no redundant filler. Every sentence adds value: the first defines the core operation, the second explains parameter usage.

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 rich input schema (100% parameter descriptions) and the presence of annotations, the description is fairly complete. It mentions the output type (downloadable MIDI file) and the key mode distinction. It lacks details about return format or edge cases, but the schema covers parameter specifics.

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

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

Schema description coverage is 100%, so all parameters already have descriptions. The tool description merely reiterates the midi_mode parameter without adding new semantic meaning beyond what the schema provides. Thus the baseline of 3 applies.

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 converts audio to a downloadable MIDI file, specifying melody or drum tracks. This distinguishes it from sibling tools like audio converter or stem splitter. The verb 'convert' and resource (audio to MIDI) are explicit.

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 specific usage guidance for midi_mode, explaining when to use 'melody' versus 'drums'. However, it does not explicitly mention when to choose this tool over alternatives or include exclusions, so it stops short of a full 5.

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 non-read-only but non-destructive behavior. The description adds input formats (MP3/WAV) and fade-in/out capabilities, but does not disclose output format or processing quirks. This adds some value beyond annotations but lacks rich behavioral detail.

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

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

Two sentences, first is front-loaded with the action, second gives usage context. No filler 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?

The tool has 9 parameters and no output schema. The description covers the core function and usage, but omits details about input options (URL vs base64 vs token), output behavior, and file size limitations. Schema fills parameter details, yet the description is minimally sufficient but not exhaustive.

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 100% parameter description coverage, so the description need not explain parameters. It does mention fade in/out, but that overlaps with schema defaults. No additional meaning beyond the schema is provided.

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 states 'Trim a section of an MP3 or WAV file with optional fade in/out,' providing a specific verb, resource, and features. This clearly distinguishes it from siblings like converter or vocal remover.

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 explicitly says 'Use this when the user wants to cut a fragment from a longer recording,' giving clear context for when to use the tool. However, it does not mention alternatives or exclusions, so it falls short of a full 5.

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 doesn't need to restate that this is a non-destructive processing operation. The description adds that it uses 'Boost Audio AI,' which hints at AI-based processing, but it doesn't disclose important behavioral traits such as what the output format is, whether processing is asynchronous, or any file size/format limitations. Thus, it adds only marginal transparency 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 two efficient sentences with no filler. It front-loads the core action ('Separate vocals from instrumental') and follows with a clear use case. Every word earns its place, making it an excellent example of conciseness.

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?

While the schema and annotations provide some context (e.g., widget-based upload, safety profile), the description omits what the tool returns. With no output schema, the agent doesn't know if the result is a download link, two separate tracks, or a widget update. For a processing tool like this, that missing output specification leaves the description incomplete.

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 100% coverage with detailed descriptions for all five parameters (audio_url, file_name, file_type, file_token, audio_base64), so the schema already explains parameter semantics. The description contributes no additional parameter-level insight, leaving the baseline at 3.

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: 'Separate vocals from instrumental in MP3/WAV using Boost Audio AI.' It specifies the resource (vocals/instrumental) and format, and the use case ('isolate vocals or get an instrumental version') helps distinguish it from generic audio tools. However, it does not explicitly mention alternatives like boost_audio_stem_splitter for multi-stem separation, so it falls short of a perfect 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 an explicit when-to-use instruction: 'Use this when the user wants to isolate vocals (acapella) or get an instrumental version of a song.' This is clear and actionable. But it lacks when-not-to-use guidance or alternatives, such as suggesting a stem splitter for more granular separation, so it doesn't reach the highest bar.

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