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

With no annotations, the description carries the behavioral burden and does well by disclosing that the full text is written to a file (not occupying conversation) and that only a summary hint and path are returned. It stops short of mentioning file overwrite behavior, permissions, or failure modes, but the most important side effects are revealed.

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 no filler. Each sentence contributes either the core behavior or parameter semantics. It is an appropriate size for a two-parameter tool.

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 and has an output schema, so the description doesn't need to detail return values. However, the '平台同上' reference is not self-contained for an agent that lacks broader context, and the out_dir default mismatch is a real gap that could lead to incorrect invocation assumptions.

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 does add meaning to both parameters: url is a video link and out_dir is the destination directory. However, '平台同上' is not self-contained, and the stated default '/tmp/video-mcp' conflicts with the schema's default of '', creating ambiguity about actual behavior.

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 action ('提取视频完整字幕/口播文案') on a clear resource (video transcript) and explains the key output behavior (write to file, return path). This naturally distinguishes it from the sibling summarize_video, which would produce a summary rather than the full transcript.

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 intended use is implied: use this tool when you need the full transcript saved to a file rather than a summary. However, it never names summarize_video or explicitly says when not to use this tool, so the routing decision is left 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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It states that subtitles or spoken text are extracted and a Markdown summary is generated, but does not mention potential failure modes, dependence on subtitle availability, network access, rate limits, or processing behavior.

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, front-loaded with the core action and output, and uses a clear Args section for parameter details. Every sentence contributes useful 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?

With only two simple parameters and an output schema present, the description gives enough to invoke the tool correctly for typical cases. However, it lacks guidance on edge cases, such as videos without subtitles or unsupported URL variants, and does not clarify how it differs operationally from get_transcript.

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%, but the description compensates by explaining that 'url' is a video share link and listing supported domains, and that 'lang' controls the output language with a default of 'zh'. This adds practical meaning beyond the bare schema fields.

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 verb ('summarize'), a clear resource ('video link'), and the main output ('Markdown summary'). It also enumerates supported platforms (B站/YouTube/抖音), making the tool's scope explicit and distinguishing it from the sibling get_transcript, though not by direct comparison.

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 what the tool does and which URL patterns are accepted, but it gives no guidance on when to choose summarize_video vs get_transcript. It does not mention any exclusions, prerequisites, or scenarios where one tool should be preferred over the other.

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