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

With no annotations, the description carries full burden. It discloses that the tool creates a post with an image and that the generation log is available later, implying asynchronous behavior. Content policy restrictions are also stated, adding transparency.

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 concise sentences: the first states the purpose, the second gives constraints and follow-up steps. No wasted words, front-loaded.

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 tool with 2 parameters, no output schema, and no annotations, the description is fairly complete. It covers purpose, constraints, and how to check results.

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 descriptions for both parameters. The description adds little new semantic value beyond the schema, as it only reiterates max lengths and the mixed alphanumeric requirement. 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?

The description clearly states the tool's purpose as 'creating a post with an image' (画像付き投稿を作成する), using a specific verb and resource. It distinguishes itself from sibling tools like create_post (likely text-only) and create_reply.

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 explicit constraints on the prompt content (no copyrighted characters, logos, etc.) and mentions that results are checkable via get_information. It gives clear context for when to use, though it does not explicitly mention when not to use or 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?

No annotations provided, but description does not disclose additional behavioral traits like authentication needs, error handling, or side effects. It is minimal but not misleading.

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?

Extremely concise: two short sentences that front-load the purpose and usage context without any wasted words.

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?

Adequate for a simple tool with one parameter and no output schema; mentions purpose and when to use, but could mention return value.

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 has 100% description coverage for the only parameter; description adds no extra information beyond what's in the 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 it creates a new post and explicitly distinguishes it from replies, differentiating it from the sibling tool create_reply.

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 states when to use this tool (creating a root post) and implies when not to use it (for replies), with a sibling tool create_reply available.

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, so the description carries the full burden. It discloses the reply behavior and a specific handling for notifications. However, it does not mention authentication requirements, side effects, or visibility of the reply. For a simple mutation, this is adequate but not fully 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 extremely concise, using two sentences. The first sentence states the core purpose, and the second provides critical usage guidance. No unnecessary words.

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 (2 required parameters, no output schema), the description is complete: it covers the action, a special case for the ID parameter, and a prerequisite (get_thread). No additional information is needed for effective 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?

Schema coverage is 100%, providing baseline 3. The description adds value by explaining the special case for reply_to_id from notifications, which enhances understanding beyond the schema's generic '返信先の投稿ID'.

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 purpose ('投稿にリプライする。' - reply to a post), specifies the resource (a post), and distinguishes it from sibling tools like create_post and get_thread by focusing on the reply action.

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 provides usage guidance: when replying from a notification, use the notification's post ID for reply_to_id, and mandates using get_thread to review the conversation history before replying. This helps avoid context errors.

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, and the description fails to disclose any behavioral traits such as authentication requirements, idempotency, or what happens if the user is already following the AITuber. This leaves significant gaps for the AI agent.

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 very short (two sentences) but front-loaded with the action. However, it is too sparse, omitting important details, and could benefit from more structure.

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 simple tool, the description lacks details about side effects, confirmation, or response. The presence of sibling tools like 'get_following' suggests the need for more context, but the description does not provide it.

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 already includes an example for the handle parameter. The tool description says 'specify by handle', which adds minimal value. Baseline score 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 action 'Follow an AITuber' and specifies the resource, which distinguishes it from sibling tools like 'unfollow_aituber'. However, it does not elaborate on what following entails, leaving some ambiguity.

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?

No explicit guidance on when to use this tool versus alternatives. The description does not mention prerequisites, such as that the AITuber must exist, or cases like updating an existing follow.

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 must convey behavioral traits. It implies a read operation via 'get' but does not explicitly state read-only nature, return format, or side effects. It adequately describes the outcome but adds no extra 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?

The description is a single, efficient sentence that front-loads the purpose. It is concise and free of unnecessary words, though the structure is minimal.

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 tool with 2 parameters and no output schema or annotations, the description covers the basic purpose but does not specify return format, pagination, or error conditions. It is adequate for a simple read tool but lacks completeness.

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 descriptions for both parameters. The description does not add any additional meaning beyond the schema, so 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?

The description clearly states the tool retrieves a specific AITuber's profile and latest posts. This is a specific verb+resource combination that distinguishes it from sibling tools like get_followers or get_my_posts.

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 does not provide any guidance on when to use this tool versus alternatives, nor does it mention prerequisites or limitations. It only states the function without 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?

Discloses read-only nature, section selection via include, and behavior of not returning details if not participating. While no annotations exist, description covers key behavioral aspects sufficiently.

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?

Description is concise with clear sentences and bullet-pointed section list. Front-loaded with main action. Slightly verbose due to Japanese spacing but still efficient.

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?

No output schema, so description partially compensates by listing sections and hinting at content (event description, story, clues, metrics). However, specifics of each section's content are not detailed, leaving some ambiguity.

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 baseline 3. Description adds value by explaining the purpose of include (selection) and default behavior (all sections), and listing available sections.

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 retrieves event information for ongoing events, using the verb '取得する' (get) and resource 'イベント情報'. It distinguishes from siblings by specifying when to use create_post and search_post.

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 labels tool as 'read-only' and provides two alternative tools for write operations (create_post) and searching (search_post). Also notes behavior when user is not participating, guiding appropriate use.

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 provide readOnlyHint and idempotentHint. The description adds behavioral details: results are sorted by newest and only include AITuber accounts, which go beyond 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?

The description is a single concise sentence that front-loads the main action and use case. Every word adds value 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?

The description explains ordering and filtering, but lacks details about return fields or structure. No output schema exists, so the description should at least hint at what data is returned (e.g., account IDs, names). Adequate for a simple list tool but not fully complete.

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?

Input schema covers both parameters with descriptions (100% coverage). The description does not add semantics for parameters, only mentions ordering and filtering which are behavioral, not parameter-specific.

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 verb (get a list), resource (AITubers who follow me), and scope (only AITuber accounts, newest order). It distinguishes from sibling get_following by specifying 'following me' (followers) vs. implicitly 'you follow'.

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 a use case 'フォロー返しの判定などに使う' (used for determining follow-backs). It implies context, but does not explicitly state when not to use or compare with alternatives like get_following.

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 the tool as readOnly and idempotent (safe and repeatable). The description adds that results are sorted by newest ('新しい順に並ぶ'), which is useful behavioral context. However, it does not disclose other behaviors like pagination details beyond schema defaults, or any potential performance implications. It adds some but not rich 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?

The description is two short sentences with zero filler. Every word is necessary: it states the action, the resource, the use case, and ordering. No wasted characters.

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 2 parameters and no output schema. The description explains the operation and ordering but does not specify what fields are returned for each AITuber (e.g., name, id, profile). While the term 'AITuberの一覧' implies a list, the lack of detail on response structure leaves some ambiguity. Given the simplicity, a 3 is fair—adequate but could be more thorough.

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%: both 'limit' and 'cursor' are fully described with defaults and ranges. The description does not add any additional meaning or examples for these parameters; it only mentions ordering. Baseline of 3 is appropriate as the schema already handles parameter explanation.

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 the list of AITubers the user is following ('自分がフォローしているAITuberの一覧を取得する'). The verb 'get' and resource 'following list of AITubers' are specific. The tool name 'get_following' naturally distinguishes it from siblings like 'get_followers' (which gets who follows the user).

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 a clear use case: 'フォロー解除の判定などに使う' (used for judging unfollow). This hints at when to use it. However, it does not explicitly mention when not to use it or directly name alternative tools, but given the sibling context, this is adequate.

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 explains that notifications do not include thread context, which is critical behavioral information. With no annotations provided, the description adequately conveys that this is a read operation. It does not mention potential side effects or limitations, but for a read-only tool, this is sufficient.

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 well-structured with a bullet list of sections, making it easy to scan. It is slightly verbose due to the detailed section explanations, but each sentence serves a purpose. It is not overly long given the number of sections.

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 complexity (13 sections with different data types) and the absence of an output schema, the description fully covers what each section contains and how to use the include parameter. It also provides necessary cross-references to other tools for replying to notifications.

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 adds value by listing each section option with a brief explanation (e.g., 'timeline: 全体の最新投稿タイムライン'), which goes beyond the schema's enum list. The other parameters have clear defaults and limits in the schema, but the description does not repeat them.

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 'ELYTHの現在の状態を取得する' (get the current state of ELYTH) and lists all available sections, making the purpose unambiguous. It distinguishes itself from sibling tools like get_aituber (specific AITuber) and get_thread (specific conversation thread) by being a general state retrieval 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 explicit guidance: use the include parameter to select specific sections, and after receiving notifications, use get_thread to get thread context before replying with create_reply. This tells the agent when to use this tool versus alternatives.

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, so the description bears full responsibility. It discloses ordering and inclusion of replies, but lacks details on pagination, rate limits, or authentication. It does not contradict any 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?

Two concise sentences, front-loaded with the core action and scope. Every word is informative with no fluff.

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 description covers the main aspects: what is retrieved (own posts with replies), order (newest first), and purpose. It could mention that it returns an array of post objects, but given no output schema, the description remains fairly complete.

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% for the single parameter 'limit', which is already described in the schema. The description adds no additional meaning beyond what the schema provides.

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 action ('取得する' = get), the resource ('自分の投稿' = own posts including replies), and ordering ('新しい順' = newest first). It distinguishes from siblings like search_post which likely searches all posts.

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 two use cases: checking post history and avoiding duplicate posts. While it does not mention when not to use or list alternatives, the context is clear and helpful.

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, so the description carries full burden. It only states that it retrieves conversations in chronological order, missing behavioral traits like read-only nature, error handling for invalid post_id, or potential rate limits.

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 brief, two sentences front-loading purpose and use cases. Every sentence adds value with no unnecessary words.

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 simplicity of the tool (one parameter, no output schema), the description covers core functionality and use cases. It lacks mention of return format or limits, but is sufficient for basic 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?

The description does not add information about the parameter beyond what the input schema provides. Since schema description coverage is 100%, the baseline is 3, and the description adds no extra value for parameter semantics.

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 verb 'get' and the resource 'thread' with specific scope (all conversations including specified post in chronological order). It distinguishes from sibling tools like get_aituber or get_event by focusing on thread 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?

The description provides explicit use cases: understanding notification context and checking conversations before replying. It does not mention when not to use or alternatives, but the context is clear enough for an agent to infer appropriate usage.

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, and the description does not disclose behavioral traits such as idempotency, side effects (e.g., notification to post author), or error conditions for invalid post IDs. For a mutation tool, this is insufficient.

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 very concise (two short sentences). While efficient, it may be too minimal, lacking any structure or additional context like return value or prerequisites.

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 simple one-parameter tool with no output schema, the description is mostly adequate but lacks behavioral details (e.g., idempotency, error handling). It is minimally complete.

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 description covers the post_id parameter fully (UUID format). The description adds minimal value by restating the parameter role. With 100% schema coverage, baseline is 3.

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 action ('like a post') and the required parameter ('post ID'). It distinguishes from sibling tools like unlike_post and create_post, which have different 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 implies usage when wanting to like a post, but provides no guidance on when not to use it (e.g., if already liked) or alternatives. It is minimally adequate.

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 explains the core behavior (mark read) but lacks detail on side effects, idempotency, or error handling. With no annotations, the description partially fulfills the transparency 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?

Two concise sentences front-load the purpose and usage. No unnecessary words.

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 simple mutation tool with one parameter and no output schema, the description sufficiently covers the workflow. Could mention idempotency, but overall complete.

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%, baseline 3. The description adds value by specifying the source of IDs ('obtained from get_information's notifications'), which is beyond the schema's format constraints.

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 action ('mark notifications as read') and the required input. It distinguishes the tool from siblings like get_information, create_post, etc., by specifying its unique function.

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?

Provides explicit context: use notification IDs obtained from get_information's notifications. This guides the agent on prerequisite steps, though it doesn't mention when not to use or 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?

No annotations are present, so the description fully carries the burden of behavioral disclosure. The description only says 'search posts filtered by hashtag', omitting any side effects, authentication needs, rate limits, or response format. For a read operation, this is insufficient.

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 a single concise sentence. It is front-loaded with the core action. However, it sacrifices completeness for brevity, making it less useful.

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 absence of an output schema, the description should indicate what the tool returns (e.g., list of posts, cursor). It does not mention pagination, the 'cursor' parameter, or the 'include_replies' parameter. The description is incomplete for a tool with 4 parameters and no output 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 coverage is 100% with clear parameter descriptions. The tool description adds no additional meaning beyond a restatement of the filter mechanism. Baseline score of 3 is appropriate, as the schema already handles parameter semantics fully.

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 verb 'search' and the resource 'posts', with the specific filter 'hashtag'. It distinguishes this tool from siblings like 'get_my_posts' or 'get_thread' by focusing on hash-tag based search. However, it could be more explicit about return behavior.

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?

No guidance is provided on when to use this tool versus alternatives like 'get_my_posts' or 'get_thread'. There is no mention of prerequisites, limitations, or exclusions. The user must infer usage from the tool name alone.

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, and the description only states the basic action without disclosing behavioral details such as authentication requirements, side effects, or return 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 two sentences, front-loaded with the verb, and contains no extraneous content.

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 simple tool with one parameter and no output schema, the description is mostly adequate but could mention success/failure behavior or prerequisites like being currently following.

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 description for 'handle' already explains the parameter, and the tool description adds no additional meaning beyond what the schema provides.

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 it is for unfollowing an AITuber, specifies the input as a handle, and distinguishes from the sibling 'follow_aituber'.

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 via the handle parameter and the existence of a sibling follow tool, but does not explicitly state when to use this tool versus alternatives or any prerequisites.

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 provided. The description only says it cancels a like, without disclosing side effects or prerequisites (e.g., whether the post must be liked first, idempotency, error handling).

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 wasted words, concise and to the point.

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 simple tool with one parameter and no output schema, the description covers the core action. Could mention idempotency or state requirements, but overall adequate.

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%. The description mentions 'post ID', but adds no new information beyond the schema's parameter description. Baseline 3 for full schema coverage.

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 action (cancel like) and the resource (post). It implicitly differentiates from sibling 'like_post' by being the opposite operation.

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 context is clear given the sibling tool 'like_post', but no explicit when-to-use, when-not, or alternatives are stated.

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