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

With no annotations, the description must carry the behavioral burden; it usefully discloses that output is a new MP4 (source not modified in place) and that paths are sandboxed to ~/Videos. It omits key write-tool behavior: whether an existing output file is overwritten, what happens on invalid SRT or codec failure, and processing time for long videos.

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, zero filler, with the core action front-loaded and the path constraint immediately after. Nothing to cut and nothing buried.

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 3-parameter mutation with no annotations and no output schema, the description covers the action, the output type, and the directory restriction. It stops short of overwrite semantics, failure modes, and what is returned (e.g. path to the new file), which an agent needs before invoking a write 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 description coverage is 0%, so the description must compensate; it does add meaningful semantics — 'subtitles' is an SRT file, 'output' is an MP4, both constrained to ~/Videos. It still leaves path form ambiguous (absolute vs relative to ~/Videos, filename vs full path) and doesn't map 'input' explicitly, so compensation is partial.

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?

States a specific verb and resource: 'Render an SRT subtitle file permanently into a video' with the outcome 'saves a new MP4'. The distinction from siblings (video_probe, trim_video, extract_audio) is obvious by operation, but the description never names or contrasts them, so it sits at a clear-but-undifferentiated 4.

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 operational constraint 'Both files and output must stay in ~/Videos' is a genuine usage rule an agent needs before calling. However there is no when-to-use/when-not guidance, no prerequisites (e.g. ffmpeg), and no statement about re-running or overwriting, so usage is only implied.

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 behavioral burden. It usefully discloses that the original is unchanged and the output format is MP3, but it omits overwrite behavior, error handling, permission needs, and what is returned after extraction.

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 short, front-loaded sentences with no filler. The core operation and the non-destructive guarantee are stated immediately.

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 three-parameter file-transformation tool with no annotations, 0% schema coverage, and no output schema, the description leaves important gaps: bitrate semantics, output path behavior, overwrite policy, and return value. It is not complete enough for confident invocation without inspecting the 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?

Schema description coverage is 0%, so the description must compensate. It gives some meaning for input (a media file in ~/Videos) and output format (MP3), but does not explain the bitrate parameter at all, nor whether output is a path, filename, or directory.

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 (extract) and resource (audio from a media file), and specifies format (MP3) and location (~/Videos). It distinguishes the operation from the sibling video tools implicitly, though it never names an alternative or explicitly contrasts itself with 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?

Usage is only implied by the purpose statement; there is no explicit condition for when to choose this tool over video_probe, trim_video, or burn_subtitles. No exclusions, prerequisites, or alternative routing are stated.

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 load; it earns credit for stating the original file is unchanged (non-destructive) and that output is a new MP4. However it says nothing about what happens if the output path already exists, permission/media-tool requirements, failure modes, or whether large durations are throttled.

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 with the core action and the key units/non-destructive note front-loaded. No filler, nothing repeated from the schema.

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?

A mutation tool with no annotations, no output schema, and 0% schema description coverage needs more than what's here. It covers safety and units but omits the quality parameter, output-overwrite semantics, and error/return behavior, so an agent still has gaps before calling confidently.

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 0%, so the description must compensate; it does explain that start and duration are in seconds and that input/output are video paths. But the quality parameter (high/medium/small) is never mentioned, nor are path format expectations (absolute vs relative, resolution against ~/Videos), leaving part of the 5-parameter surface undocumented.

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?

States a specific verb and resource ('Cut a segment from a video') plus the output artifact ('save a new MP4') and the working location (~/Videos). It doesn't explicitly differentiate from video_probe, extract_audio, or burn_subtitles, but those operations are distinct enough that an agent can route without confusion.

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?

Usage is implied by the operation itself ('trim') and constrained to files in ~/Videos, but there is no explicit when-to-use guidance, no exclusion of alternatives, and no statement of what to do instead if the file is elsewhere.

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 at all, the description carries the full behavioral burden and does not meet it. It never states that the operation is read-only, what happens if the file does not exist, whether the workspace path is a requirement or a restriction, or roughly what metadata comes back.

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 short sentence with no filler and the resource front-loaded. It is efficient, though the brevity is part of why other dimensions are under-specified rather than a virtue in itself.

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 (one required parameter, no nested objects), but with no output schema the description is the only place that could explain what 'media metadata' contains (duration, codec, resolution) and what a failure looks like. It omits both, leaving the agent guessing about the return payload.

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 single 'file' parameter has 0% schema description coverage, so the description must compensate. It only adds the 'inside the Videos workspace' scoping; it does not say whether the value is a bare filename, a relative path, or an ID, nor any format 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?

Names a specific verb and resource ('Return media metadata') plus a scope ('inside the Videos workspace'), which implicitly separates it from the transformation siblings trim_video, extract_audio and burn_subtitles. It does not explicitly state that it is the read-only inspection step versus those tools, so it stops short of a 5.

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

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

There is no stated when-to-use, when-not-to-use, or named alternative. An agent must infer that this is the tool to call before trimming or extracting audio; nothing in the text says so.

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