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

With no annotations, the description minimally discloses that IDs are not URLs but does not mention whether adding a duplicate is safe, if the operation is idempotent, or any error conditions. A mutation tool should provide more 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?

Two sentences, no filler. Front-loaded with the core action and key constraint. Every word earns its place.

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

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

Despite simplicity, the description omits important context for a mutation tool: no mention of success/failure indicators, duplicate handling, or permission requirements. Leaves an AI agent underinformed for safe 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?

Schema coverage is 100%, but the description adds value by clarifying that both parameters are YouTube IDs and not URLs, which disambiguates potential misinterpretation. This is a meaningful addition 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 the action ('Add a video to an existing playlist') and the resource, distinguishing it from siblings like create_playlist. The clarification that IDs are YouTube IDs (not URLs) further sharpens purpose.

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 on when to use this tool versus alternatives, prerequisites (e.g., playlist existence), or edge cases (e.g., duplicate video). The description is purely operational without directional help.

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 provided, so description carries full burden. Only mentions default privacy but omits other behaviors like authentication, side effects, or error 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?

Two concise sentences with front-loaded purpose. No redundant info, though could include more detail without bloating.

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?

Covers main purpose and key default, but lacks details about return value or success response. Adequate for a simple creation 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?

Input schema has 0% coverage; description hints at privacy_status via default but does not explain title or description parameters. Inadequate for a 3-param 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 verb 'create', resource 'playlist', and context 'on authenticated channel'. It also notes the default privacy setting, distinguishing it from siblings like add_to_playlist.

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 on when to use this tool versus alternatives (e.g., adding to existing playlist). Lacks when-not or scenario 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?

No annotations are provided, so the description carries the full burden. It states it deletes a caption track, indicating a destructive operation, but it does not mention authorization, rate limits, error behavior (e.g., if ID does not exist), or whether the deletion is irreversible.

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 no redundant information. The purpose is front-loaded, and the usage guidance follows naturally. Every word earns its place.

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

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

Given the tool's simplicity (one parameter, no output schema, no nested objects), the description covers the essential purpose and prerequisite. However, it could be more complete by noting any irreversible nature or confirmation behavior, but overall it is adequate for an agent to use correctly.

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

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

The input schema desccription for caption_id is 'Caption track ID to delete.', which already conveys the parameter's purpose. The tool description adds no additional semantics beyond what the schema provides. Since schema description coverage is 100%, 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 uses a specific verb 'delete' and resource 'caption track', clearly stating the action and how to identify the track (by ID). It also distinguishes from siblings by referencing list_captions to find the ID.

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 advises using list_captions first to obtain the track ID, providing a necessary prerequisite. It does not elaborate on when not to use the tool, but for a delete operation, this is reasonable.

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?

Discloses irreversible deletion and the confirmation guard, which is key behavioral context. Without annotations, this provides necessary transparency, though permissions or side effects are omitted.

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 core purpose, no wasted words.

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 simple tool with 2 fully-described parameters and no output schema, the description covers all essential aspects: purpose, safety guard, and irreversibility.

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?

Adds meaning beyond schema by explaining why confirm_video_title is needed (prevents accidental deletion) and that deletion is irreversible. Schema descriptions are clear, but description enriches understanding.

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

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

Description clearly states 'Permanently delete a video', using specific verb and resource. Distinguishes from siblings like 'delete_caption' which deletes a different resource.

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 explicit when-to-use or when-not-to-use guidance. While the safety guard implies careful usage, alternative tools or conditions are not mentioned.

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

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

No annotations are provided, so the description carries the full burden. It mentions authentication ('for the authenticated channel') and the filter, but does not disclose behavioral traits like pagination, rate limits, or return format.

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 main purpose. Efficiently communicates the core functionality without excessive verbosity.

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

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

Given no annotations and no output schema, the description provides adequate context for a query tool but lacks details about return values and behavioral aspects that could be expected from sibling tools.

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

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

Schema description coverage is 67%, so baseline is 3. The description adds that the tool applies a Shorts filter on top of usual knobs, but does not elaborate on parameters like sort or max_results 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 it queries YouTube Analytics restricted to Shorts for the authenticated channel, using a specific filter. It distinguishes itself from sibling tools like query_channel_analytics, which likely covers all content.

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 for Shorts analytics by mentioning the filter, and the sibling set includes query_channel_analytics for general analytics. However, it does not explicitly state when not to use or provide 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?

No annotations are provided, so the description must convey behavior. It indicates a read operation by 'Fetch full details', but does not explicitly state it is read-only, idempotent, or what happens on failure (e.g., missing video). The listing of returned fields adds some transparency.

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

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

The description is a single sentence that efficiently conveys the action and what is returned, with no extraneous words. It is appropriately sized for the tool's simplicity.

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

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

Given the simple single-parameter schema and no output schema, the description adequately covers the tool's purpose and output. It could mention error behavior or prerequisites (e.g., video must exist), but overall it provides enough context for this straightforward 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?

With 100% schema description coverage, the baseline is 3. The description adds practical guidance: 'the part after v= in the URL', which helps the agent correctly format the video_id parameter, going beyond the schema's own description.

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 'Fetch full details for one video by ID', specifying the resource (video) and action (fetch), and lists the exact details returned (snippet, status, statistics, duration). This distinguishes it from sibling tools like delete_video or update_video_metadata.

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 needing full details for a single video but provides no explicit guidance on when to use this tool versus alternatives (e.g., list_my_videos for multiple videos) or conditions where it should not be used.

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 provided; description only states what is listed without mentioning behavioral traits like pagination, read-only nature, 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?

Single sentence that is clear and to the point, with no unnecessary 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?

Lists fields returned, which compensates partially for missing output schema; but does not mention output format or pagination.

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% and description adds no additional meaning beyond the schema's description of video_id.

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

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

Description clearly states it lists caption tracks on a video and specifies fields returned (language, name, status, draft status). Distinguishes from sibling tools like delete_caption and upload_caption.

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 explicit guidance on when to use this tool versus alternatives, but context of siblings (e.g., delete_caption) implies it is used for viewing before other actions.

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, and the description does not disclose behavioral traits such as authentication requirements, rate limits, or side effects. It only states ordering and return fields, leaving gaps in transparency 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, front-loaded sentence with no extraneous information. It efficiently conveys the core purpose and return 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?

While the description mentions return fields, it lacks context on pagination, authentication, rate limits, or whether replies are included. For a simple listing tool, it is adequate but has notable gaps.

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 50% (only video_id has a description). The description adds no additional parameter semantics beyond the schema, leaving max_results undefined in meaning and constraints.

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'), resource ('top-level comment threads on a video'), ordering ('newest first'), and return fields ('comment IDs, authors, text, and like counts'). It distinguishes from sibling tools like moderate_comment and reply_to_comment.

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 for listing comments, but does not provide explicit guidance on when to use this tool versus alternatives (e.g., for replies, nested comments). No conditions or exclusions are mentioned.

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 explains the scanning and filtering behavior, but does not disclose return format, performance implications, or authentication requirements.

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

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

The description is a single concise sentence with no wasted words, efficiently conveying the tool's function.

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

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

The description lacks information about the return value (fields, structure), pagination, or ordering, which is important given no 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 parameter is fully described in the schema; the description adds context about why it scans recent uploads, but adds minimal extra 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 clearly states the tool lists recent Shorts by scanning uploads and filtering by duration ≤60s, distinguishing it from siblings like list_my_videos.

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

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

The description mentions it is useful when the Data API lacks a direct Shorts filter, but does not specify when not to use it or suggest 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, the description carries the full burden. It transparently states the operation is a read-only list ('list videos'), specifies ordering, and lists return fields. It does not mention pagination behavior or rate limits, but for a straightforward list tool, this is adequate and does not mislead.

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, well-structured sentence that front-loads the main purpose and includes key details (ordering, return fields). Every part earns its place; no unnecessary words.

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

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

Given no output schema, the description does explain return values. However, it omits pagination behavior (how to use page_token) and does not differentiate from sibling tools. It is adequate for a simple list but could be more complete with pagination details.

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

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

The schema has 2 parameters with 0% description coverage, meaning no parameter descriptions exist in the schema. The description adds no explanation for 'max_results' or 'page_token', failing to compensate for the schema gap. The only info is that the list is paginated (implied by page_token) but not stated explicitly.

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

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

The description clearly states the verb 'list', the resource 'videos on the authenticated channel', and specifies ordering ('newest first via the uploads playlist'). It also enumerates the returned fields (IDs, titles, view counts, privacy status). This differentiates it from sibling tools like 'list_my_shorts' (shorts) and 'get_video' (single video).

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 for listing own videos but provides no explicit guidance on when to use this tool versus alternatives (e.g., 'list_my_shorts' for shorts or 'get_video' for details). No when-not-to-use or prerequisites are mentioned. The context is implied but not clarified.

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 full burden. It discloses the effects of each status (hides, approves, deletes) but does not mention required permissions, reversibility, or side effects. This is adequate but not comprehensive.

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

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

The description is a single sentence that efficiently conveys the tool's purpose and the three possible statuses. It is front-loaded with the action and resource, with no extraneous words.

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 mutation tool with 2 parameters and no output schema, the description covers the core functionality. It explains the purpose, the status options, and their effects. It could mention success/error behavior or authentication needs, but it is fairly complete given 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 description adds meaning to the 'moderation_status' parameter by explaining the result of each enum value, which goes beyond the schema's brief enum description. However, it does not clarify 'comment_id', which is a simple identifier and may be self-explanatory.

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 'Change the moderation status of a comment' with explicit enumeration of the three possible statuses and their effects. It distinguishes the tool from sibling tools like list_comments or reply_to_comment by focusing solely on moderation 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 for moderating a comment but provides no explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. The purpose is clear from context, but the description lacks explicit when/when-not instructions.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns tabular data and supports date-range and optional grouping, but does not mention authentication requirements, rate limits, error handling, or pagination behavior. The description provides some transparency but is incomplete.

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 contains no unnecessary words. Every sentence adds value, making it highly concise and well-structured.

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

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

Given the tool has 7 parameters and no output schema, the description is brief. It does not explain the return format beyond 'tabular data', lacks details on error handling or edge cases, and does not cover how to interpret results. This leaves gaps for an agent using the tool in complex 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 high (86%), so the schema already documents parameters well. The description adds minimal value beyond the schema, only referencing date-range and optional grouping. It does not provide additional semantic meaning for parameters like 'filters' or 'sort'.

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

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

The description clearly states it queries YouTube Analytics for the authenticated channel, specifying it returns tabular data for common metrics like views and watch-time. The verb 'Query' and resource 'YouTube Analytics for the authenticated channel' are specific, and it distinguishes from siblings like 'get_shorts_analytics' by being for general channel analytics.

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 mentions the tool is useful for certain reports but does not explicitly say when to use it versus alternatives like 'get_shorts_analytics'. There is no guidance on when not to use it or exclusions, leaving the agent to infer usage context.

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 provided; description only notes scope requirement. Does not disclose mutation behavior, idempotency, error responses, or return value.

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 compact sentences conveying purpose and requirement with no extraneous content.

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 and minimal description; missing details on expected return, error handling, or post-conditions for a write operation.

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 covers parent_id with clear description, but text param lacks description. Tool description adds no parameter information beyond schema, not compensating for the 50% coverage gap.

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 verb 'reply' and resource 'top-level comment', with scope requirement. Distinguishes from sibling tools like list_comments or moderate_comment.

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 on when to use this tool versus alternatives such as moderate_comment or add_to_playlist. Only mentions required OAuth scope.

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 full burden. It describes the update operation but does not disclose side effects, auth requirements, rate limits, or whether changes are irreversible. The partial update hint is helpful but not exhaustive.

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, no redundancy. The purpose is front-loaded, and the partial update instruction is concise.

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 6-parameter tool with no output schema, the description covers the essential update semantics. It implies that only provided fields are changed, which is critical. Could mention that omitted fields remain unchanged, but it's already clear from 'Only provide fields you want changed.'

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 low (17% – only category_id has a description). The description compensates by listing the fields and emphasizing partial updates, adding meaning beyond the schema's property names and types. However, it does not explain formatting for tags or category_id further.

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

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

The description clearly states it updates video metadata, listing specific fields (title, description, tags, category, privacy). This distinguishes it from sibling tools like delete_video or get_video.

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 'Only provide fields you want changed,' indicating a partial update pattern. It does not explicitly state when to use vs. alternatives, but the context is clear.

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

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

No annotations are provided, so the description carries full burden. It mentions 'creates a new track' implying mutation, but lacks details on idempotency, conflict behavior (e.g., does it overwrite or fail if track with same name+language exists?), authentication needs, or rate limits. This is a significant gap for a creation tool.

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

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

Two clear, front-loaded sentences with no redundant information. The first sentence states the primary purpose, and the second adds practical usage tips. Every word earns its place.

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

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

Given the presence of siblings for deletion and listing, the description is fairly complete for a creation tool. It covers formats and draft usage. However, it lacks details on error handling, file size limits, or post-creation behavior, leaving some gaps for a comprehensive understanding.

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

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

Schema coverage is 100%, so all parameters have descriptions. The description adds value beyond the schema by providing usage context for `name` and `is_draft`, but for other parameters, it repeats schema info. Baseline 3 is appropriate.

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

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

The description clearly states it uploads a caption track (SRT or WebVTT) to a video, specifying that it creates a new track. This distinguishes it from siblings like list_captions (listing) and delete_caption (deletion), providing specific verb and resource.

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 actionable guidance: use a distinct `name` per language/track, or `is_draft=true` while iterating. However, it does not explicitly state when not to use it (e.g., for updates, consider deleting first, referencing the sibling delete_caption), so some exclusions are missing.

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