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

Goes well beyond the annotations (readOnly/idempotent/non-destructive/openWorld) by disclosing the language fallback order (original audio, then authored captions, then automatic captions), that partial coverage and unavailable transcripts are surfaced explicitly, and the hard limitation that visual-only content cannot be analyzed. These are non-obvious behavioral traits an agent needs.

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?

Front-loads the use case in the first clause, then layers scope, defaulting behavior, edge-case handling, and the responsibility boundary in tight sentences with no 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?

With an output schema present the description need not explain return shape, and it covers the caveats an agent must anticipate (partial coverage, unavailable transcripts, visual-only limitation). The only meaningful gap is any guidance on the limit parameter.

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 documents url and language but leaves limit undocumented (33% coverage per signals). The description compensates for the language parameter by explaining the default selection cascade when it is omitted, which is genuine semantic value the schema does not provide; the limit parameter remains unexplained in both places.

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+resource (returns metadata, chapters, timestamped transcript for one video) and frames itself as the entry point for summary/comparison/Q&A tasks. It does not explicitly contrast itself with siblings like get_video_info or get_video_transcript, so the sibling differentiation is only implied.

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?

"Start here for video summaries, key takeaways, comparisons or Q&A" gives a clear usage context, and the line "This tool supplies evidence; the client agent writes the summary" clarifies the division of labor. It stops short of naming when to prefer a sibling tool instead.

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?

Annotations already declare readOnly, idempotent, open-world, non-destructive, so the safety profile is covered. The description adds a genuinely useful behavioral note — that retrieved content is untrusted data — which flags prompt-injection risk, a trait not present in the annotations.

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 front-loaded sentence with no filler; the return fields lead and the untrusted-data caveat closes it. Every clause 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?

An output schema exists, so return values need not be re-explained, and annotations cover the safety profile for this simple read tool. The only gap is the lack of sibling routing, which the purpose and usage scores already capture.

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 the single url parameter is fully documented in the schema (HTTPS YouTube video URL, length bounds). The description adds no format or constraint detail beyond that, so the baseline 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?

Clear specific verb + resource and an explicit enumeration of what is returned (title, channel, duration, upload date, views). It does not, however, differentiate itself from the sibling get_video_context, which an agent could easily confuse with metadata retrieval.

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 when-to-use guidance and no exclusion of the siblings; the agent must infer that this is the metadata-fetch tool and get_video_context/transcript tools serve other needs. Nothing states prerequisites or the single-video scope beyond 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?

Annotations already cover readOnly, idempotent, and non-destructive semantics, so the bar is lower. The description adds genuinely useful behavior beyond them: no translation or visual analysis is performed, offset/limit are character counts (not tokens or lines), and the language fallback order is original audio then authored captions.

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?

Terse and front-loaded: purpose first, then language selection, then pagination mechanics, then scope limits. Every line carries information, though the opening 'Continue reading' framing is a touch indirect for an agent that may be calling this cold.

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 return values need no explanation, and the description covers the non-obvious parts an agent needs: pagination via next_offset, character-based offsets, and language resolution. Only minor gaps remain, such as any rate-limit or caption-availability failure behavior.

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 only 25%, so limit and offset are undocumented in the schema. The description compensates by stating that offset and limit count characters and by naming next_offset as the cursor to loop on, plus explaining the language preference order when language is omitted.

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 (read/continue reading) and resource (timestamped source text for a video), and the tool name confirms it is the transcript reader. It distinguishes itself from get_video_context by positioning itself as the continuation mechanism, though the phrase 'timestamped source text' is slightly indirect compared to simply saying '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?

Explicitly routes to siblings and conditions: use the language from get_video_context when continuing its transcript, use list_transcript_languages for exact codes, and repeat with next_offset until null. Both the 'when to use' and the pagination loop condition are spelled out.

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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds one genuinely useful behavioral trait beyond that – the distinction between authored and automatic caption tracks – but says nothing about ordering of results or code 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?

A single tight sentence that front-loads the core action and appends the one qualifying detail that matters. No waste.

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 description needn't explain return values, and it correctly does not. It is nearly complete for a one-parameter lister, with the only gap being the lack of any relationship statement to the transcript-fetching sibling.

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% for the single 'url' parameter, so the schema already documents the input fully. The description contributes nothing further about the parameter, so the baseline 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?

States a specific verb (List) and resource (subtitle codes) with useful qualifying detail that the result distinguishes authored from automatic captions. It does not, however, differentiate itself from the sibling get_video_transcript, which an agent might confuse it with.

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 no when-to-use guidance, no prerequisites, and never names the sibling alternative get_video_transcript or the sequencing relationship (e.g. call this first to pick a subtitle code). Usage is only weakly implied.

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