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 search runs 'in parallel' and 'Returns aggregated results with file paths,' which gives some behavioral insight. However, it does not mention potential resource intensity from parallel workers, model download behavior, or whether files are modified (though 'search' implies read-only). It is not completely vague but lacks deeper behavioral 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 three sentences: the first states the core function, the second provides a use case, and the third describes the return value. There is no fluff or repetition. Every sentence earns its place, and the key 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?

For a tool with 4 parameters, no output schema, and no annotations, the description gives the essential purpose, use case, and return format. It does not explain the aggregation format in detail or mention any constraints, but given the simplicity of the tool (search and return results), it is largely sufficient. The lack of output schema is partially mitigated by saying 'aggregated results with file paths.'

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 the baseline is 3. Each parameter (audio_paths, keywords, workers, model_size) already has a description in the schema, including the important note to 'ALWAYS use tiny unless...' for model_size. The description text itself adds no extra parameter meaning, but since the schema covers all parameters, score 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: 'Search multiple audio files for keywords in parallel.' It identifies the resource (audio files), the operation (search), and the distinguishing feature (parallel, multiple files). This separates it from sibling tools like 'search_audio' which likely handles single files, and 'deep_search' which may imply a different scope.

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 strong usage context by mentioning 'Ideal for processing podcast libraries, interview collections, or any batch of audio files.' This implies when to use it (batch scenarios), but it does not explicitly mention when not to use it or name alternative tools (e.g., 'use search_audio for single files'). This is clear context without exclusions, fitting score 4.

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 does not state what the tool returns, whether it modifies files, or any side effects. The word 'auto-detect' implies a read-only operation, but no details are given.

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, clear sentence with no fluff. It quickly communicates the tool's core purpose without unnecessary detail, making it easy to parse.

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 three parameters, no output schema, and no annotations. The description does not explain the output format, expected behavior, or how chapters are returned. This lack of contextual information makes it incomplete for an agent to use effectively.

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 covers 100% of parameters with detailed descriptions, including guidance on model_size and sensitivity. The description itself adds no additional parameter meaning, so baseline score 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 'Auto-detect topic chapters in audio' clearly states the tool's function with a specific verb ('detect') and resource ('topic chapters'). It distinguishes itself from sibling tools like transcribe_audio or identify_speakers by focusing on chapter segmentation.

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 does not mention exclusions or alternative tools, leaving the agent to infer usage solely from the purpose.

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, the description must disclose behavioral traits. It states the action and purpose but does not explain the consequences (e.g., whether all memories are deleted, if it is irreversible, or if it affects transcriptions). The word 'clear' hints at destruction but is insufficiently detailed.

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, concise sentence that is front-loaded with the action and outcome. Every word contributes meaning, and there is no redundant or irrelevant information.

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 potentially destructive nature of clearing memory, the description lacks important context such as whether the operation is reversible, what exactly gets deleted, and success/failure behavior. No output schema exists, so the description should explain more. It is too sparse for safe usage.

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 no parameters, so the baseline for 0 parameters is 4. There is nothing to compensate for, and the description does not need to explain 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 uses a specific verb ('clear') and resource ('transcription memory'), and the purpose ('to free disk space') is explicitly stated. This clearly distinguishes it from sibling tools like memory_stats or list_memories, which have different actions.

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 when disk space needs to be freed, but it lacks explicit when-to-use or when-not-to-use guidance and does not mention alternatives. It gives a clear context but no exclusions or comparisons to sibling tools.

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, the description carries the burden. It discloses a key behavioral trait: 'Downloads only the requested segment — not the full video.' It also mentions broad site support. However, it does not describe potential side effects like network usage, file format, or failure modes, and it lacks any detail about authentication 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 three concise sentences, each adding value. It leads with the action, clarifies behavioral scope, gives a use case, and states supported sites. No redundant wording.

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

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

For a tool with 5 params and no output schema, the description covers purpose, key behavior, use case, and platform support. It doesn't explain return values or output file specifics, but those are partly covered by parameter descriptions. Given the sibling context, this is adequately complete 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?

Schema description coverage is 100% with all parameters already documented. The description adds minimal extra semantics beyond the schema, such as 'specific time range' which maps to start/end, but does not provide syntax or format details beyond what the schema already contains. Baseline 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 tool's function: 'Export a video clip from a URL for a specific time range.' It also differentiates from siblings by emphasizing that it downloads only the requested segment, not the full video, which is distinct from audio-focused tools like download_audio or transcribe_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 implies when to use it: 'Perfect for extracting moments around keyword matches.' However, it does not explicitly mention when not to use it or contrast with alternative tools like download_audio or highlights. The use case is clear but not exhaustive.

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 discloses nothing about return format, side effects, or operational behavior—just a tagline. This is a significant gap for a tool that could be read-only or have download/implications.

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 concise sentence, but it's under-specified for a 9-parameter tool. It's memorable but doesn't provide enough operational detail to guide an agent, so it's not appropriately sized for the tool's complexity.

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 description lacks essential context: what results look like, when to set clip, how output is returned, and how it differs from sibling tools. Given the high parameter count, rich schema, and no output schema, this bare-bones description is insufficient for correct invocation.

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 itself adds no parameter information, but the schema provides detailed descriptions for all 9 parameters (100% coverage), including specific guidance like 'ALWAYS use tiny unless the user explicitly requests a different size.' This meets the baseline for high 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 identifies the tool as a semantic audio search ('Search audio by meaning'), which distinguishes it from keyword-based search. However, it doesn't explicitly state the output (e.g., timestamps or matches) nor name sibling tools, so it's clear but not fully differentiated.

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 offers no guidance on when to use deep_search versus alternatives like search_audio or batch_search. It doesn't mention any prerequisites, use cases, or exclusions, leaving the agent to infer entirely from the schema.

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 some behaviors: audio-only, speed optimizations via aria2c, and broad site support. However, it does not mention return values, error handling, prerequisites (e.g., network), or side effects like directory creation/overwrite, leaving gaps for an 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 a single paragraph with the purpose front-loaded, followed by the key usage note. It is somewhat long but every sentence adds value, with the exception of 'Built by Augent' which is mildly redundant. Overall 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?

There is no output schema and no annotations. The description explains the tool's purpose and usage well but fails to clarify what the tool returns (e.g., file path, success message) or behavior on failure. This missing information is significant for an agent to confidently use the 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 coverage is 100% with both parameters described. The description adds context about supported sites and the 'audio only' behavior, but it does not meaningfully extend the schema descriptions for url or output_dir. 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 downloads audio from video URLs, explicitly notes it downloads audio only (never video), and lists supported platforms. This distinguishes it from sibling tools like transcribe_audio and search_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?

It gives explicit when-to-use guidance: 'When a user pastes ANY URL and asks what was said... use this tool to download, then transcribe_audio' and directly warns against WebFetch for media URLs. This provides strong context for choosing the tool over 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. It discloses AI-driven selection criteria, returns timestamps and text, and explicitly states the calling agent decides which to export. Minor gap: it doesn't mention dependencies like 'audio must be transcribed' or the side effects of clip export, but these are covered in the schema.

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 sentences, front-loaded with the core purpose, and every sentence earns its place. There is no fluff or repetition, making it easy for an agent 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 7-parameter complexity and absence of an output schema, the description sufficiently explains return values (timestamps and text) and the decision workflow. The schema covers parameter details and prerequisites, so the tool is reasonably complete for an agent to invoke 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 description coverage is 100%, so the baseline is 3. The tool description adds a high-level mode distinction ('auto' vs 'focused') but doesn't provide additional parameter-level semantics beyond what the schema already explains for each parameter.

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?

Clearly states the verb and resource ('Export MP4 clips of specific moments') and immediately distinguishes two modes (auto and focused). This differentiates it from sibling tools like transcribe_audio or search_audio, making the tool's purpose unmistakable.

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 each mode ('Omit for auto mode' vs 'Provide a topic, person, concept...'), but it does not explicitly contrast with alternative sibling tools such as search_audio or clip_export. It gives solid usage direction within the tool itself.

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, the description is the only source of behavioral disclosure, but it only restates the high-level function. It does not mention output format, limitations, whether any model or download is required, or what 'who speaks when' returns. The schema provides model_size guidance, but the description itself adds no behavioral 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 a single front-loaded sentence with no filler, repetition, or irrelevant detail. It is optimally concise, even though more content could be added for completeness in other dimensions.

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?

This is a speaker-diarization tool with no output schema and no annotations, but the description does not describe the output format (e.g., speaker segments or timestamps) or any prerequisites. While the schema covers parameters well, the overall tool context is incomplete for an agent to know what result to expect.

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 the baseline is 3. The description itself adds no parameter explanation beyond the schema, though the schema already includes useful guidance such as 'ALWAYS use tiny unless the user explicitly requests a different size.'

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 'Identify who speaks when in audio' uses a specific verb and resource, clearly indicating speaker diarization. It is distinct in meaning from sibling tools like transcribe_audio or separate_audio, but it does not explicitly name alternatives or scope, so it misses the top 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?

No guidance is provided on when to use this tool versus alternatives such as transcribe_audio or separate_audio. It neither states use cases, prerequisites, nor exclusions, just a functional one-liner.

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, the description carries the full burden of behavioral disclosure, but it only says 'List media files in a directory' without detailing return format, sorting, or file type specifics. It does not reveal limitations like hidden files or symlink handling.

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 concise sentence with no filler words. It is front-loaded with the action and resource, earning a high score for 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?

Given the tool's simplicity and full schema coverage, the description is minimally viable but leaves gaps such as return format and scope of 'media files'. The absence of annotations and output schema means the description should have provided more 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?

All three parameters have schema descriptions, so the baseline is 3. The description doesn't add any parameter semantics beyond the schema, making it adequate but not enhanced.

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

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

The description clearly states the verb 'List' and the resource 'media files in a directory', making the tool's purpose immediately obvious. It is distinct from sibling tools like search_audio and list_memories, though it does not explicitly name alternatives.

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, nor any context about prerequisites or exclusions. It simply states the operation without addressing usage scenarios.

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 must carry behavioral disclosure. It reveals that this is a listing operation returning specific fields, which implies a read-only, non-destructive action. However, it does not mention pagination, ordering, or whether 'all' means no filtering, leaving some behavior implicit.

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 with the core action front-loaded. Every word adds value: 'List all stored transcriptions' states purpose, followed by a practical use case. 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?

For a zero-parameter listing tool with no output schema, the description adequately covers what it does and when to use it. It could potentially mention how it relates to list_files or whether the markdown paths are local paths, but for its simple complexity, the description is sufficiently 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?

The input schema has no parameters, so the baseline is 4. The description adds no parameter information, but none is needed. It clarifies what the returned fields are, providing some semantic context despite the absence of 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 uses a specific verb ('List') and a clear resource ('all stored transcriptions') with the exact fields returned. It distinguishes itself from sibling tools by focusing on transcription metadata and markdown file paths, which is distinct from search-oriented tools like search_memory or list_files.

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 phrase 'Useful for browsing what has already been transcribed' clearly indicates a primary use case. It doesn't explicitly name alternatives or exclusions, but the context is sufficiently clear for a simple listing tool.

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 burden of behavioral disclosure. The verb 'View' implies a read-only operation, and the description mentions what information is returned, but it does not explicitly state that there are no side effects or mention any permissions or limitations. 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 a single, front-loaded sentence that immediately states the action and resource, followed by specific details. Every word earns its place, with no redundancy or 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?

For a simple tool with no parameters and no output schema, the description adequately covers purpose and the key return values (stored file count and total duration). It could be slightly more explicit about the read-only nature, but overall it is complete enough for the tool's simplicity.

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 there is nothing to explain. The schema coverage is vacuously 100%, and the description does not need to elaborate on parameters. A baseline of 4 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 uses the specific verb 'View' and identifies the resource as 'transcription memory statistics', then details exactly what statistics are included (number of stored files and total duration). This clearly distinguishes it from sibling tools like clear_memory or list_memories, which have different purposes.

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 that the tool is for viewing summary statistics about transcription memory, so the usage context is inferable. However, there is no explicit mention of when to prefer this over alternatives like list_memories, nor any exclusion criteria.

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 burden of behavioral context. It discloses that the tool mutates files (migrates .md files), computes links, generates MOC files, and is safe to run repeatedly. It does not detail potential side effects (e.g., overwriting existing files) but does state idempotency ('Safe to run repeatedly'), which is valuable behavioral information.

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 adding meaningful information: the core action, the three sub-tasks, and the safe-to-re-run guidance. No wasted words, and it is front-loaded with the main verb and resource.

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 mutates files and has no output schema, the description explains the transformation and hub generation, which is complete enough for a one-time migration tool. It could mention that it is a post-transcription step, but the 'upgrade existing memory' phrase implies that. The only slight gap is lack of explicit mention of any risks (e.g., changing file contents), but 'safe to run repeatedly' mitigates that.

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 only parameter, min_moc_members, is fully described in the schema (100% coverage). The description mentions 'generates MOC hub files for tag clusters', which gives context for the parameter's purpose. Since schema coverage is 100%, the description adds minimal extra value but the schema itself is sufficient.

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 a specific verb ('Rebuild') and resource ('Obsidian graph view data for all transcriptions'). It clearly distinguishes from siblings by naming the specific actions: migrating .md files to YAML frontmatter, computing [[wikilinks]], and generating MOC files. This is a unique purpose among sibling 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 says 'Run this once to upgrade existing memory for Obsidian' and 'Safe to run repeatedly', implying it is an initialization/upgrade tool. It doesn't explicitly say when not to use it or compare to alternatives, but the context is clear enough for an agent to recognize it as a one-time migration task.

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, the description bears the full burden of behavioral disclosure. It mentions the output format but omits that the tool relies on Whisper transcription, potential performance costs, or prerequisites like audio-download status. This is a significant 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?

Two tight sentences: the first specifies the action and output, the second gives usage context. 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?

For a tool with 7 parameters, no output schema, and no annotations, this description is too thin. It fails to explain operational behavior like transcription dependency, clip export requirements, or how this integrates with downloaded audio.

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% and each parameter (including model_size and clip) has detailed guidance. The description adds no parameter-specific information, so the baseline score 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?

Clearly states the tool searches audio files for keywords and returns timestamped matches with context snippets. The verb+resource+output structure distinguishes it from siblings like transcribe_audio or search_proximity.

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 a clear use case ('finding specific moments in podcasts, interviews, lectures') but doesn't explicitly compare to alternative tools or state when not to use.

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 the search scope and modes, which is helpful, but it does not explain return format, result ordering, pagination, or any permissions/rate limits. For a search tool, this is acceptable but not rich; a description of the output structure would have been more 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 only three sentences, each earning its place: the first states scope, the second clarifies no audio_path, and the third explains modes. It is front-loaded and contains no redundancy or 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?

The tool has 6 parameters and no output schema, so the description should compensate by explaining what the agent can expect in return. While the parameter descriptions cover input semantics, the description does not provide any return value details, result format, or behavioral constraints (e.g., how results are scored or sorted). This is a notable gap for an agent.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining the default mode ('keyword' = literal match) and how to use semantic mode, which is not fully captured in the schema. It also clarifies that no audio_path is needed, reinforcing the query scope. This extra context raises the score above 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 searches across ALL stored transcriptions, with a specific verb ('Search'), a defined resource ('ALL stored transcriptions'), and scope that distinguishes it from siblings like search_audio ('No audio_path needed'). It also introduces the two modes, leaving no ambiguity about what the tool does.

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 tells when to use this tool ('No audio_path needed, queries everything in memory') and provides guidance on mode selection ('Default mode is keyword... Use semantic mode for meaning-based search'). It doesn't mention alternatives like deep_search or batch_search, so it lacks full exclusions, but the guidance is clear enough for most use cases.

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 only states the purpose and gives an example, without indicating read-only nature, output format, error conditions, or any side effects. This is a significant gap 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 two sentences, front-loaded with the main purpose, and uses no redundant words. It efficiently conveys the core function and a practical example.

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 six parameters and no output schema, yet the description does not explain what the tool returns (e.g., timestamps, snippets) or mention varying behavior for different parameter settings. While the schema covers parameter details, the description should provide more context about expected results and limitations, making it only partially 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 100%, so the schema fully documents each parameter. The description adds an illustrative example but does not explain parameter nuances or usage details beyond what the schema provides. Baseline 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 specific action ('Find where one keyword appears near another keyword in audio') and includes a concrete example ('startup' near 'funding'). This distinguishes it from sibling tools like search_audio by highlighting the proximity-based search mechanism.

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 a clear use case ('Useful for finding contextual discussions'), signaling when to use this tool. However, it does not explicitly mention alternatives or when not to use it, so it falls short of full guidelines.

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 for behavioral disclosure. It does convey the isolation behavior and stem outputs, but it omits side effects like output file locations, processing time/resource usage, or whether the original audio is modified. This is a moderate gap given the lack of 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 two sentences, front-loaded with the core purpose, and includes a practical usage recommendation. Every sentence contributes meaning without repetition 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?

The description covers the tool's purpose, method (Demucs v4), and usage scenario, which is sufficient for a straightforward audio-processing tool. However, it lacks details about expected outputs (e.g., files created) and prerequisites or limitations, but given the no-output-schema context, it is reasonably 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 100%, so the parameters are already well-documented in the input schema. The description adds some context by mentioning the specific stems and the vocals focus, but it doesn't elaborate on the model parameter or vocals_only behavior beyond what the schema already provides.

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 separates audio into specific stems (vocals, drums, bass, other) using Meta's Demucs v4, which directly conveys its function. It also differentiates from sibling tools like transcribe_audio by focusing on the separation use case and explicitly tying it to cleaning audio before transcription.

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 guidance on when to use the tool: 'Use this before transcription when audio has music, intros, or heavy background noise for dramatically cleaner results.' This provides clear context and links to a sibling tool, though it doesn't mention when not to use it or alternative tools beyond transcription.

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, the description carries the burden of disclosing behavior. It mentions that downloads return a recording_id, that status can be checked, and that live recordings can be stopped. However, it lacks details on authentication requirements, side effects like file persistence, or any non-obvious operational constraints.

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 concise and well-structured. It leads with the core purpose, then enumerates the three modes in a clear numbered list. Every sentence provides essential 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?

The tool has three distinct modes and four parameters, and the description covers the primary scenarios comprehensively. It does not detail the output format for status checks or error conditions, but the absence of an output schema and the clarity of the modes make this acceptable.

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?

Although the input schema already describes each parameter well (100% coverage), the description adds semantic connections by explaining the three modes: how url initiates a download, how recording_id serves for status/stop, and how stop modifies behavior. This goes beyond the schema's individual descriptions.

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 or live-record a Twitter/X Space.' It uses specific verbs and a specific resource, and outlines three distinct usage modes, which distinguishes it from sibling tools like download_audio or transcribe_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 clear context for when to use each mode: pass url to start a download, pass recording_id to check status, and pass recording_id with stop=true to stop a live recording. However, it does not explicitly compare with alternative tools or mention when not to use it.

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 actions (add, remove, list) but does not disclose side effects, prerequisites (e.g., valid cache_key), reversibility, or return format for the 'list' action. This is a significant gap for a tool that 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 two sentences long, front-loads the primary action, and provides relevant context about tag usage. Every sentence earns its place with no redundancy or irrelevant detail.

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 is simple (3 parameters, no output schema) and the description covers its core purpose. However, it omits behavioral details like what 'list' returns or whether tags are case-sensitive, which would be useful given the lack of annotations and output schema. It is adequate but has room for improvement.

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 each parameter described in detail, including constraints and examples for 'tags' and an enum for 'action'. The description adds no new parameter-specific meaning beyond reinforcing that tags are broad topic categories, which is already in the schema. This matches the baseline for high 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 function: 'Add, remove, or list tags on a transcription.' This is a specific verb+resource combination. It also explains that tags are 'broad topic categories' for organizing memories, which adds helpful context. However, it does not explicitly distinguish this tool from sibling tools like 'chapters' or 'highlights' that also operate on transcriptions.

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 for when to use the tool: tags help 'organize and filter memories in the Web UI.' This implies the tool is for categorizing transcriptions with broad topics. It does not mention exclusions or alternatives, but the context is sufficient for an agent to infer appropriate usage.

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, the description carries the full burden and discloses key behaviors: downloads audio, transcribes, saves .md to Desktop, returns audio_path, and supports a save_content mode. It could add more detail about failure modes or time costs, but the core side effects are clearly stated.

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 sentences pack a lot of information without being bloated. It front-loads the main purpose, then explains the pipeline, follow-up use, and save mode. Slightly dense but each sentence contributes distinct value.

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 complex 7-parameter tool with no output schema and no annotations, the description is remarkably complete: it explains the full pipeline, the return value, the save_content alternative, and gives guidance on style and model size. This is sufficient for an agent to invoke the tool correctly in most scenarios.

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 already provides descriptions for all 7 parameters (100% coverage), so the baseline is 3. The description adds some operational context (e.g., model_size 'ALWAYS use tiny', style selection logic, save_content as separate mode) but does not significantly extend beyond what the schema already defines.

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 specific verbs and resources: 'Take notes from a URL', 'Downloads audio, transcribes, and saves .md to Desktop'. It clearly differentiates itself from sibling tools by stating it handles the entire pipeline (download, transcribe, save) for note-related requests, and also covers the save_content variant.

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?

Explicitly states when to use this tool: whenever the user asks for notes, summaries, highlights, takeaways, eye-candy, quiz, or any formatted content from a video/audio URL. It also clarifies the save_content workflow ('no url needed') and mentions return of audio_path for follow-up tools like chapters and search, effectively guiding selection among siblings.

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 the asynchronous behavior (returns job_id), the output (MP3 file), and the file_path side effects (strips markdown, skips metadata, embeds audio player). This is strong behavioral detail, though it could be more explicit about status response contents or permissions.

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 concise, with every sentence contributing valuable information: purpose, output, background behavior, and two usage modes. It is well-structured and front-loaded with the core function, with no unnecessary repetition.

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 (async workflow, multiple modes, no output schema), the description covers the essential workflow: initial call, job_id polling, and both text and file_path input. It misses details like status response format or error handling, but the description is sufficiently complete for an agent 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 description coverage is 100%, so the schema already documents all parameters. The description adds workflow context (e.g., passing job_id to check status) but largely repeats the schema's parameter descriptions. It does not add significant new semantics beyond the schema.

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

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

The description clearly states 'Convert text to natural speech audio using Kokoro TTS' and 'Saves an MP3 file', giving a specific verb and resource. This distinguishes it from sibling tools like transcribe_audio and download_audio, which serve opposite or different functions.

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 explains the usage pattern: 'Runs in background — returns a job_id immediately. Call again with job_id to check status.' It also distinguishes between raw text and file_path modes. However, it does not explicitly name sibling tools or state when not to use it, so it falls short of a perfect score.

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 must carry the full burden of behavioral disclosure. It only mentions that the tool returns full text with timestamps, omitting side effects such as audio file requirements, model download behavior, optional output file writing, or the special translated_text short-circuit path. The schema covers some parameters, but the description itself adds minimal behavioral depth.

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 concise sentences, front-loading the core action and purpose. Every sentence earns its place, with no redundancy or 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?

Given the rich schema with full parameter descriptions and no output schema, the description sufficiently covers the tool's purpose and usage context. It explains the return value (full text with timestamps) and differentiates from search. Some behaviors (like the recommended model size) are left to the schema but are still covered, making the overall definition quite 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 100%, so the baseline is 3. The description does not add any parameter-level meaning beyond the schema, but the schema descriptions are already rich (e.g., model_size includes a strong guideline to always use tiny). The description's high-level context is helpful but not parameter-specific.

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: "Transcribe an audio file and return the full text with timestamps." It uses a specific verb+resource and distinguishes from sibling search tools by noting its utility is for complete transcription "rather than searching for specific keywords."

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 context: use this tool when you need the complete transcription, not for keyword search. It implies the alternative (search tools) but does not name a specific sibling or mention other exclusions such as when to use a batch or speaker-identification tool. This is clear context without exhaustive exclusions.

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, the description carries the full burden. It discloses that frames are stored in augent memory, embedded as Obsidian wikilinks, and describes auto/manual/assist mode behaviors. It does not cover all edge cases (e.g., errors, download behavior), but provides substantial behavioral 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 slightly longer than necessary but well-structured, front-loading the critical usage restriction and then compactly describing modes. Each sentence contributes, though the mode enumeration could be more terse.

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 (11 params, no output schema), the description covers the core functional behavior, modes, and storage details. It does not detail the exact return format for query or assist outputs, but offers enough for an agent to invoke correctly in most scenarios.

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 the baseline is 3. The description adds value by explaining how the modes (query, auto, manual, assist) correspond to parameters like `query`, `auto`, `timestamps`, and `assist`. It also notes `video_path` can be output from `clip_export`, linking to a sibling tool.

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: extract visual context from videos at relevant moments. It is distinguished from sibling tools by explicitly limiting usage to visual requests and providing mode breakdowns (query, auto, manual, assist).

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 explicit when-to-use ('ONLY call this tool when the user explicitly asks for visual context') and when-not-to ('Do NOT call it alongside take_notes or download_audio unless the user specifically requests visuals'). It also gives mode selection guidance, which is an alternative-aware usage guide.

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