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

With no annotations, the description carries the full behavioral burden. It discloses fallback behavior ('Falls back to any available'), the effect of timestamps, and the max_chars cutoff. It does not explicitly state read-only status, but 'fetch' implies a non-mutating operation.

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

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

The description is compact and front-loaded with the core purpose, followed by a tight bullet-style parameter list. Every line adds distinct value and there is no redundant or filler 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?

With an output schema present, the tool's return shape is covered elsewhere. The description addresses parameter semantics, input variants, and behavioral fallbacks. Minor gaps include lack of explicit error behavior when captions are unavailable, but overall it is sufficient 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?

Schema description coverage is 0%, so the description must fully compensate. It explains each parameter with concrete formats, examples, defaults, and behavioral effects, giving the agent everything needed to provide valid inputs.

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

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

The description opens with a specific verb and resource: 'Fetch a YouTube video's captions as text.' This clearly identifies the tool's function and distinguishes it from siblings like get_video_info or list_channel_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 gives useful input-format context (URL types, language fallback) but does not explicitly state when to choose this tool over siblings or mention any exclusions. Usage is implied rather than directed.

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 usefully discloses that the tool uses oembed and requires no API key, which is meaningful behavioral context. However, it does not explicitly state that the operation is read-only or describe error handling, rate limits, or unsupported URL formats.

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 compact sentence that front-loads the returned data and includes a useful parenthetical about authentication. Every word earns its place and nothing is redundant.

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 single-parameter tool with an output schema, the description is largely complete: it states the resource, the returned fields, and the auth-free mechanism. It only lacks explicit usage boundaries relative to siblings and any note on URL constraints.

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 0% description coverage for the only parameter, url. The description adds that the URL should point to a YouTube video and that it yields metadata via oembed. This is helpful for a single obvious parameter, but it does not specify accepted URL variants or validation rules.

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 names a specific resource (a YouTube video) and the exact data returned (title, channel name, thumbnail), plus the implementation method (oembed, no key). It distinguishes this from sibling tools like get_transcript and list_channel_videos, though it does not use an explicit verb like 'retrieves'.

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?

There is no explicit guidance on when to use this tool versus siblings. The mention of oembed and 'no key' implies a low-friction metadata lookup, but it never states when to prefer it over get_transcript or list_channel_videos, leaving the choice to inference.

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 approximate limit (~15) and accepted channel formats, but does not mention pagination, ordering, whether it's a read-only operation, or what happens with invalid channels. The '~15' caveat is a small transparency credit, but significant behavioral gaps remain.

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

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

One sentence with no wasted words. The key scoping detail ('up to ~15') is front-loaded, and the channel format clarification is compact and directly useful.

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 (2 params, no nested objects) and has an output schema, so the description doesn't need to explain return values. However, with no annotations, it should disclose more about behavior: ordering, recency definition, error cases, and whether the limit is a hard cap. The channel format guidance is good, but the missing behavioral context leaves it slightly incomplete.

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

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

Schema description coverage is 0%, so the description must compensate. It explains the 'channel' parameter's accepted formats, which adds real meaning beyond the schema. However, it does not explain the 'limit' parameter's behavior beyond the default, and the schema already provides the default value. Partial compensation for a low-coverage schema.

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

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

The description clearly states the tool lists the latest videos of a channel, with a specific resource (channel) and a scope qualifier (up to ~15). It distinguishes itself from siblings like get_transcript and get_video_info, which focus on individual videos, though it doesn't explicitly name them.

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: use this when you need a channel's recent videos. It does not explicitly state when not to use it or mention alternatives like watch_channels for monitoring. The channel format guidance ('@handle, UC... id, or channel URL') is useful but doesn't address selection criteria 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 stateful side effect ('mark them seen'), the 'since the last call' behavior, the first-run cap, and the channels.json fallback with an environment variable. It does not cover auth or rate limits, but the key behavioral traits are 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 three short sentences with the core behavior front-loaded. Every sentence adds operational value—core action, channel input syntax, and the first-run edge case—with no filler or repetition of schema defaults.

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?

An output schema exists, so describing return values is unnecessary. The state directory, environment variable, default path, and first-run behavior are covered, but languages and with_transcript have no semantic explanation anywhere, and there is no guidance about prerequisites or error cases.

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

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

Schema description coverage is 0%, so the description must compensate. It adds real meaning for 'channels' ('@handles / UC ids', empty means read channels.json) and mentions max_new_per_channel for first-run behavior, but leaves languages and with_transcript entirely unexplained beyond their parameter titles.

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

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

The description opens with a specific verb and resource: 'Return videos published since the last call and mark them seen.' This clearly distinguishes watch_channels from list_channel_videos by emphasizing stateful filtering and a side effect, so an agent can tell them apart without opening schemas.

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 a polling/check-for-new-videos use case and explains input behavior, but it never explicitly says when to prefer this tool over siblings like list_channel_videos. The 'since the last call' wording gives context, yet no exclusions or alternatives are named.

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