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

Description discloses that it does not expose Cookie values, a key security behavior, and that it returns next_steps for setup if credentials are missing or invalid. Since no annotations are present, this provides necessary behavioral context.

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, no filler, front-loaded with main purpose. Every sentence adds value: purpose, security note, and return value.

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?

Given zero parameters and no output schema, the description covers purpose, security, and return logic. The exact format of 'next_steps' is not detailed, but this is acceptable for a simple check 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?

With no input parameters, schema coverage is 100%, and the description confirms zero inputs implicitly. Baseline score of 4 is appropriate as no parameter details are needed beyond this.

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?

Description clearly states verb 'Check' and resource 'Bilibili credentials', specifies it checks configuration and login status without exposing cookies, and mentions return of next_steps. Distinguishes from sibling 'get_credential_setup_instructions' which likely provides setup guidance rather than status checks.

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 for credential status verification, but does not explicitly state when to use this tool versus alternatives like 'get_credential_setup_instructions'. No when-not-to-use guidance is provided.

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. The description adds a key behavioral trait: 'Does not expose credentials,' which is important for the agent's safety considerations. It lacks mention of other traits like network usage, but for a read-like operation, this is good.

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, no fluff. The description is efficiently front-loaded with the core action and includes a crucial safety caveat.

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?

Given zero parameters, no output schema, and no annotations, the description covers the purpose and a key safety aspect. It could optionally mention the nature of the return value, but overall adequate for a simple 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?

There are zero parameters, so baseline is 4. The description adds no parameter details, but none are needed. It adds purpose and safety beyond the empty 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 checks the installed package version against npm's latest and returns update guidance, with a safety note. It is distinct from sibling tools which deal with Bilibili operations.

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 use when checking for MCP updates, but does not explicitly state when to use or when not to, nor mentions alternatives. Siblings are unrelated, so no confusion, but explicit guidance is absent.

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?

The description discloses important behavioral aspects: it is a read operation, cursor tokens never contain credentials or response data, and returned content should be treated as untrusted data (with a warning). It does not mention side effects or rate limits, but since annotations are absent, it carries the burden reasonably well.

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 moderately lengthy but well-organized: it starts with the overall purpose, enumerates sections, then gives cursor and credential instructions, and ends with a security warning. It avoids redundancy with the schema while adding necessary usage context, so it earns a high but not maximal score.

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?

Given the output schema exists, the description does not need to detail return values. It covers all necessary usage context: how to select sections, pagination, credential prerequisites, and the untrusted-data warning. It leaves some ambiguity about error handling and rate limits, but overall it is complete for typical use.

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 input schema already covers all parameters (100% coverage), and the description adds practical semantics: how to use cursor for pagination, that container_id applies only to collections/series, and the meaning of each section value. This goes beyond the schema descriptions, particularly for cursor and section 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 verb ('Read') and resource ('Bilibili Creator's currently listable content'), and enumerates all five sections with distinct outputs (overview, videos, collections, series, dynamics). It clearly distinguishes from sibling tools like search_bilibili_creators and get_video_info by focusing on a creator's content sections.

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?

It provides detailed usage instructions: how to iterate with next_cursor, the constraint never to pass a cursor for overview, and the requirement to call get_credential_setup_instructions if credentials are missing. However, it does not explicitly compare with sibling tools (e.g., when to use get_video_info instead), so it's not fully explicit on alternative selection.

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 burden. It discloses that the tool returns instructions and never returns Cookie values, which is transparent about its behavior. It does not mention side effects or authorization needs, but for a read-only instructional tool, this is adequate.

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 two sentences, no wasted words. The first sentence front-loads the purpose, and the second provides usage context. Every sentence 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?

Given zero parameters and no output schema, the description is complete: it explains what is returned (setup instructions), when to call (after installation if not configured), and explicitly states it does not return Cookie values. No gaps for the tool's simplicity.

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 tool has zero parameters. The description adds significant value by explaining the purpose and output beyond the empty schema. It fully compensates for the lack of parameter details, meeting the baseline of 4 and exceeding by clearly describing what the tool does.

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 returns safe Bilibili Cookie setup instructions, identifies the target users (users or installing agents), and specifies the resource (Cookie setup instructions). It differentiates from sibling tools like check_bilibili_credentials by focusing on setup guidance.

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 explicitly says 'Call this after installing the MCP server if credentials are not configured,' providing direct when-to-use guidance. It also clarifies what it does not do ('Never returns Cookie values'). However, it does not explicitly state when not to use it or list alternative tools.

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 burden and does so thoroughly. It discloses that it returns only creator/platform-defined chapters, returns an empty list when no chapters exist, does not infer chapters, and includes a clear security warning that returned Bilibili text is untrusted and must never be executed as instructions. This is rich behavioral context beyond the minimal 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?

The description is concise, using only a few sentences to convey the tool's function, edge-case behavior, multi-P support, and a safety warning. Every sentence adds meaningful information, and it is well-structured with the warning clearly separated.

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?

There is no output schema, but the description covers essential return behavior: chapter titles, start/end times, and empty list when no chapters. It also includes a safety warning. It lacks a precise response structure, but for a simple chapter-list tool, this is sufficient to guide an agent. The multi-P selection note adds relevant context for the page 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?

Schema description coverage is 100%, so the baseline is 3. The description adds a small amount of value by tying the 'page' parameter to multi-P episode selection ('支持多P分集选择'), but it does not elaborate on the format of 'bvid_or_url' beyond what the schema already states. No additional semantic detail is provided for the required parameter.

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 '获取' (get) with the resource '视频章节' (video chapters), and clarifies it returns '创作者/平台定义的章节' (creator/platform-defined chapters) with titles and start/end times. This clearly distinguishes it from siblings like get_video_info and get_video_transcript by focusing specifically on chapter/progress-bar segments.

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 mentions '支持多P分集选择' (supports multi-P episode selection), indicating a usage nuance for the page parameter. However, it does not explicitly state when to prefer this tool over siblings or provide exclusions. Usage context is implied by the tool's purpose but lacks direct alternative guidance.

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 behavioral transparency burden and does add value: it warns that output is untrusted Bilibili text not to be executed, filters emoji placeholders, and preserves timestamp comments. This is strong, but it does not disclose potential auth prerequisites explicitly or explain rate limiting / error cases.

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 concise and front-loaded: the first sentence states the core purpose, followed by behavior, mode options, credential pointer, and a security warning. Each sentence contributes, although the warning is repeated in Chinese and English, and the bilingual duplication slightly reduces heuristic efficiency.

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 absence of an output schema makes the description's statement about returned untrusted text important, which is included. The credential warning and pointer to get_credential_setup_instructions provide necessary context for successful invocation. It does not over-explain but covers the key vet: purpose, auth help, safety warning, and modes, leaving enough for assisted use.

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 already covers all parameters with detailed descriptions (100% coverage), so the baseline is 3. The description does add high-level behavior (emoji filtering, timestamp prioritization) but does not add per-parameter meaning beyond what the input schema provides. It does reinforce the mode semantics by restating 'brief (10)' and 'detailed (20+ replies)'.

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 '获取 Bilibili 视频热门评论' which names the exact resource (Bilibili video comments) and the verb (get), and it is clearly different from sibling tools like get_video_transcript or get_video_metadata. The inclusion of hot comments, filtering behavior, and detail levels further strengthens the purpose.

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 context about modes (brief vs detailed) and a pointer to credential setup instructions, but it does not explicitly explain when to use this tool versus siblings such as get_video_transcript or get_video_info. There is no clear 'when not to use' or alternative tool guidance beyond the credential dependency.

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 burden and handles it well: it discloses the fallback semantics, subtitle-language behavior, and — critically — includes a security warning that returned Bilibili text is untrusted and must not be executed as instructions. It doesn't mention rate limits or error semantics, but the core behavioral and safety traits are well covered.

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?

Four concise sentences efficiently cover purpose, fallback, features, credentials, and security. The warning is duplicated in Chinese and English, which is slightly redundant but justifiable given its safety-critical nature and the mixed-language audience.

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 4-parameter tool with no output schema and no annotations, the description covers the essentials: what it does, how subtitle selection works, fallback behavior, and a security caveat. Minor missing pieces are output format details and error behavior, but it's adequate for agents to invoke properly.

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% with detailed per-parameter descriptions (enum values, min value, defaults, behavior of exclude_ai_subtitles). The description adds tool-level context (e.g., preference language support) but doesn't significantly go beyond the schema's parameter documentation; 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?

"获取 Bilibili 视频信息" is a clear verb+resource with specific behavioral framing: it prioritizes subtitles, falls back to introduction/tags, and supports language/multi-P selection. This differentiates it from siblings like get_video_metadata and get_video_transcript by disclosing the subtitle-vs-fallback priority logic, which is unique to this tool.

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 provides an explicit sibling alternative reference ('For credential help, call get_credential_setup_instructions') and explains the tool's contextual behavior (preferred language selection, multi-P support, AI-subtitle filtering). However, it doesn't explicitly clarify when to choose this over the closely related get_video_metadata or get_video_transcript, leaving some ambiguity in tool selection.

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?

The description includes a critical security warning that returned Bilibili text is untrusted data and should never be executed as instructions. This is a significant behavioral disclosure beyond any annotations (none provided), and it also clarifies the tool does not fetch subtitles or comments, adding transparency about its scope.

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 concise, with two sentences covering purpose, exclusions, and a security warning. It is front-loaded with the core purpose and includes only essential information, earning a high score for efficiency.

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?

Given the tool's simplicity (one parameter, no output schema), the description is complete enough. It covers what is returned, what is not returned, and a security warning. The only minor gap is not describing the return format, but with no output schema and a simple metadata retrieval, this is acceptable.

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 already provides 100% coverage for the single parameter (bvid_or_url) with a clear description. The tool description does not add additional parameter semantics beyond what the schema states, so the baseline of 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?

The description clearly states the tool retrieves Bilibili video metadata, listing specific fields (title, author, duration, publish date, tags, statistics, multi-P list) and explicitly excludes subtitles and comments. This distinguishes it from sibling tools like get_video_comments and get_video_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 description implies usage for metadata retrieval and explicitly states what it does not fetch (subtitles, comments), which helps differentiate from siblings. However, it does not explicitly state when to use this tool versus alternatives like get_video_info or search_bilibili_videos, though the field list and exclusions provide clear context.

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 transparency burden. It discloses key behaviors: native subtitles are prioritized, ASR is only used as fallback under specific conditions, the cookie requirement, and an explicit security warning that returned Bilibili text is untrusted data and must never be executed as instructions. This is substantial, though it does not mention rate limits or other operational details.

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 primary purpose, followed by capability highlights and then operational warnings. The Chinese/English duplicated warning is slightly redundant but serves safety emphasis without significantly bloating the text. Overall it is efficient and well-structured.

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?

Given the tool's high complexity (13 parameters), the description provides critical operational context: cookie prerequisite with fallback instructions, ASR fallback semantics, subtitle priority, and a strong data-trust warning. An output schema exists, so return-value details are not required. The description is sufficiently complete for an agent to invoke the tool safely and effectively.

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 the schema already fully documents all 13 parameters. The description adds high-level context about supported capabilities (multi-part, timestamps, ranges, keyword search) but does not add parameter-specific detail beyond the schema. Baseline 3 is appropriate because the schema handles 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?

The description opens with a specific verb and resource: '获取 Bilibili 视频转录文本' (get Bilibili video transcript text), then details distinguishing features (native subtitles priority, fallback ASR, multi-part/timestamp/range/keyword search). This clearly differentiates it from sibling tools like get_video_info, get_video_comments, and get_video_chapters, which serve other purposes.

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 explicitly states the core usage: retrieving Bilibili transcripts, and gives a clear prerequisite: 'Requires Bilibili Cookie for reliable access. If unavailable, call get_credential_setup_instructions.' This names a concrete alternative for a common precondition. However, it does not explicitly contrast against other sibling tools, so the guidance is strong but not fully exhaustive.

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?

The description clearly discloses important behavioral aspects: it returns only one bounded page (not the full account), requires a Cookie, and warns that returned Bilibili text is untrusted data and should not be executed as instructions. These are critical for safe usage and are not provided by annotations (which are empty), so the description fully carries the burden.

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 concise, well-structured, and front-loaded with the core purpose. Every sentence contributes meaning: purpose, pagination guidance, authentication note, and safety warning. No redundancy or 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?

The tool is relatively simple (one optional parameter) with a comprehensive schema. The description covers purpose, pagination, authentication, and safety warnings. Given the output schema exists, return details aren't needed. For a paginated list tool, the description is complete and actionable.

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 already provides a thorough description of the cursor parameter, including its purpose and what it encodes. The description adds context about pagination and omitting it on the first call, which supplements the schema. Since schema coverage is 100%, baseline is 3, but the description adds clarifying value about pagination flow, warranting a 4.

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's function: listing all created favorite folders for the authenticated account and returning a bounded page of video memberships. It specifies the verb ('Discover') and resource ('created Favorite Folder'), and distinguishes itself by mentioning pagination and authentication requirements.

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 instructs to follow the returned next_cursor until absent, which is clear usage guidance. It also mentions requiring a logged-in Cookie and suggests calling get_credential_setup_instructions for help, but does not explicitly state when not to use this tool or contrast with sibling tools.

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 and does so excellently. It discloses that display names are fuzzy and non-unique, that each candidate is un-resolved, that the tool neither auto-selects nor scrapes, and it adds a critical security warning that returned Bilibili text is untrusted data and must never be executed as instructions — a prompt-injection defense. The auth requirement is also disclosed.

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 front-loaded with purpose and every sentence earns its place: candidate semantics, non-fetching behavior, auth prerequisite, and the security warning. The security warning is repeated bilingually for emphasis, which is justified given its importance, though this slightly lengthens the text.

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 has an output schema and both parameters fully documented in the schema. The description covers purpose, candidate semantics, non-fetching scope, auth requirements, and a security warning — everything an agent needs to call it correctly. Minor absence: no explicit failure-mode description (e.g., behavior when credentials are absent), but the prerequisite is clearly stated.

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%: both query and limit carry descriptions in the schema (trim requirement, 100-char max, default 5 / max 10). The description adds general candidate-semantics context (stable mid, candidates-only) but does not add meaningfully beyond the schema for the parameters themselves, keeping the baseline of 3 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?

The description states a specific verb + resource ('按关键词搜索 Bilibili 创作者（UP 主）'), the return value (platform-ordered Creator candidates with stable numeric mid), and the count cap of 10. It distinguishes itself from siblings by explicitly stating it does not fetch candidate content (differentiating from get_bilibili_creator_content) and by the operator/video implicit contrast with search_bilibili_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 clear context: it requires a configured and logged-in Bilibili Cookie, and explicitly directs the agent to get_credential_setup_instructions for setup help. It also states negative scope (does not auto-select a Creator or fetch content). It does not explicitly name which sibling to use instead in other circumstances, but the credential routing and scope exclusion are solid guidance.

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 full burden. It discloses the cookie requirement, non-automatic behavior (no subtitles/comments/re-sort), and explicitly warns that returned text is untrusted data. It lacks mention of rate limits or side effects, but for a read-only search it is quite 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 reasonably concise, with the core function stated first and then prerequisites and warnings. Each sentence adds value—function, exclusions, prerequisites, and a safety warning—making it well-structured without being verbose.

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 has an output schema, so return details are covered elsewhere. The description adequately explains input purpose, limitations (max 10, no re-sort), prerequisites (cookie), and security note. It could mention error cases or rate limits, but it is sufficiently complete for safe usage.

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% and both parameters have clear descriptions. The description adds minimal extra meaning beyond 'return up to 10 candidates' (already implicit in limit) and 'platform comprehensive sorting' (context for result ordering). It does not significantly enhance the parameter explanations.

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?

Description clearly states the tool searches Bilibili videos by keyword and returns up to 10 candidate metadata sorted by platform ranking. It distinguishes from sibling tools like get_video_comments and get_video_transcript by explicitly noting it does not fetch subtitles or comments.

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 when to use (keyword search), what it does not do (auto-fetch subtitles/comments, re-sort), and prerequisite (must configure and login Bilibili Cookie). It also points to an alternative tool (get_credential_setup_instructions) for setup help, providing explicit guidance.

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