YouTube Remote MCP Server

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

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: each tab yields a different item shape, and 'store (desktop only)' is a constraint not present in the annotations. Pagination behavior is implied by the paginationToken param but not discussed.

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 purpose, then the tab/return breakdown, then use cases. It is dense but nearly every clause carries information; the tab enumeration is somewhat redundant with the schema but aids scanning.

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 no output schema, the description carries the burden of explaining return values and does so thoroughly — identity fields, subscriber/view counts, social links, and per-tab item shapes. Nothing essential for correct invocation is missing.

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 the baseline is 3. The description largely restates the channelId formats (UC…, @handle) and the tab list already documented in the schema; the only genuinely new detail is that 'store' is desktop-only.

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 ('Fetches a YouTube channel by its ID or handle') and enumerates the tabs and returned identity fields. It clearly differentiates itself from the sibling youtube_video, youtube_transcript and youtube_search tools by scoping to channel-level data and noting the videoId handoff.

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?

Gives concrete use cases (monitor competitor channels, build creator directories, track posting cadence, feed videoId into the Video/Transcript endpoints), which routes the agent to the right sibling for downstream steps. It stops short of explicit when-not-to-use exclusions, 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?

Annotations already cover the safety profile (readOnlyHint, openWorldHint, destructiveHint=false), so the description's real contribution is the response-shape disclosure: the page is split into videoResults/channelResults/shortsResults/shelves/adsResults etc., each preserving positionOnPage for layout reconstruction. That is meaningful behavioral context. It adds nothing on auth, rate limits, or quota, which keeps it below a 5.

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-loaded with the core action, then the return structure, then use cases in a single dense block. Nearly every clause carries information, though the long parenthetical inventories of output fields and flags are heavy for prose that a schema would normally carry.

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 no output schema, the description takes on return-value documentation and does it well, describing each result block and the totalResults field. Combined with complete parameter coverage and annotations, an agent has enough to call the tool and interpret its output 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?

Schema description coverage is 100% and five parameters carry enums, so the schema already documents query syntax, country/language codes, the sp override, duration buckets, and feature flags. The description adds no parameter-level meaning beyond that, making the baseline 3 correct.

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 ('Searches YouTube for a query') and immediately delimits what it returns (the full results page). It also differentiates itself from siblings by naming the downstream YouTube Video, Channel, and Transcript endpoints that consume its videoId/channelId output. An agent can identify this as the YouTube search entry point without opening the schema.

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 enumerates when to use it ('competitor and topic monitoring, brand-mention tracking, ad-placement intelligence, creator discovery, trend research') and how it chains to other endpoints. It stops short of naming which sibling to prefer over an alternative (e.g. TikTok/Google SERP search for the same intent), so it is clear context without 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?

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description goes further by disclosing the response shape (segments with startMs/endMs/snippet/startTimeText plus availableTranscripts[] with language, type and selected flags) and the asr-vs-human-authored fallback behavior — useful context since there is no output schema.

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-loaded with the core purpose and return structure before the use-case list. It is a single dense paragraph whose sentences mostly earn their place, though the use-case enumeration runs somewhat long.

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 no output schema, the description compensates by explaining the transcript segment fields and the availableTranscripts listing. Together with a fully documented parameter schema and annotation-covered safety profile, an agent has everything needed to call and interpret this 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 100%, so all three parameters (v, type, languageCode) are already documented in the schema; the description's parameter notes (languageCode examples, type=asr, default track behavior) largely restate that. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Get YouTube Video Transcript... timed transcript (subtitles) of a YouTube video by its 11-character videoId'), immediately distinguishing it from the sibling video/channel/search endpoints. An agent can tell exactly what it returns without opening the schema.

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?

Gives concrete usage contexts (RAG/LLM pipelines, summaries, chapter outlines, archives, translation/accessibility, catalog analysis) and a concrete routing hint ('pair with the YouTube Channel endpoint to enumerate videos, then fetch transcripts'). It lacks an explicit 'don't use this when...' contrast against siblings like getYoutubeVideo, so it falls short of a 5.

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 read-only, non-destructive, open-world reads, so the safety profile is covered. The description adds genuine behavioral context: the exact shape of the payload (raw + normalized counts, asr caption kinds, Content-ID music matches, rail videos), which an agent cannot get elsewhere since there is no output schema.

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 purpose in the first line, then spends the bulk on the return payload enumeration, which is justified because no output schema exists. It is dense but every clause carries information; no filler sentences.

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 single-resource GET with no output schema, the description covers identity of the resource, returned fields, and usage contexts. Nothing an agent needs to call it correctly or interpret the result is missing.

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%, so all four parameters including the gl/hl codes and deviceType enum are already documented in the schema. The description's mention of the 11-character videoId only restates what the schema says, so the 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?

States a specific verb and resource (fetch a single YouTube video by ID) and immediately enumerates the returned resource's key attributes. It distinguishes itself from the youtube_transcript sibling and from channel/search siblings by scoping to one 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?

Lists concrete use cases (enrich a URL, monitor view/like growth, extract music or affiliate links, RAG features) and routes the agent to the YouTube Transcript endpoint for caption fetching. There is no explicit 'when not to use' or alternative for the search/channel siblings, so it stops short of a 5.

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