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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds context by specifying the data returned (message count, participants, action items, recent messages), which is beyond the annotations. However, it does not mention any potential limits or performance aspects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that efficiently conveys the tool's output and purpose with no wasted words. It is front-loaded with the key verb and resource.

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 5 parameters and no schema descriptions, the description is insufficient for an agent to use the tool effectively. It lacks details on how to specify time ranges or message limits. However, an output schema exists, which may explain return values. Overall, adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only implicitly mentions the 'chat' parameter ('指定聊天') but does not explain optional parameters like start_time, end_time, max_messages, or response_format. This provides minimal added meaning beyond 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 that the tool returns message count, participants, action items candidates, and recent messages for a specified chat, intended for model to generate a summary. It distinguishes from sibling tools like wechat_read_chat and wechat_search_messages by aggregating summary data.

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 explicitly state when to use this tool versus alternatives like wechat_read_chat or wechat_search_messages. Usage is implied for generating a summary, but no when-not or exclusion criteria are 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?

Annotations already mark it as read-only and idempotent. The description adds transparency by noting it uses heuristic screening, requires manual confirmation, and does not create tasks or send messages. This provides behavioral context beyond annotations, though it omits details about parameter effects.

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, focused sentence that conveys the core function and key constraint (manual confirmation). It is not verbose and front-loads the action. However, it could be expanded slightly to cover parameters or return values without becoming 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?

Given 4 parameters with 0% schema coverage and an output schema present (which may document return values), the description should explain parameter usage (e.g., which chats are scanned, limit behavior). It only addresses 'days' indirectly. The tool's context is not fully specified, leaving gaps for effective invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. However, it only implicitly references the 'days' parameter ('最近N天') and entirely ignores 'chats', 'limit', and 'response_format'. No additional meaning is provided beyond the schema's field names.

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 extracts to-do candidates from recent WeChat chats using heuristic filtering, with specific verb '筛选待办候选' and scope '最近N天的聊天文本'. It also distinguishes from automatic task creation, differentiating it from similar tools like wechat_find_todos_ui.

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 initial candidate extraction requiring human confirmation, but does not explicitly state when to use this tool versus alternatives like wechat_find_todos_ui or wechat_search_messages. No explicit when-not or exclusion criteria.

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 adds significant behavioral context beyond annotations: it runs local heuristics, requires manual confirmation, and does not write to the task system. Annotations already indicate read-only and non-destructive behavior, and the description aligns perfectly while adding actionable nuance.

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 sentence, which is concise but omits crucial parameter information. While the core purpose is front-loaded, the lack of structure (e.g., lists or bullet points) reduces its utility. It prioritizes brevity over completeness.

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 does not explain return values despite the existence of an output schema, nor does it elaborate on the 5 parameters. It also fails to differentiate from closely related sibling tools like 'wechat_find_todos'. The tool's complexity (5 params, heuristics) demands richer context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain any of the 5 parameters (chat, limit, min_score, scroll_pages, response_format). The agent cannot infer their meanings or defaults beyond basic schema types. This is a major gap for a tool with a 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 clearly states the tool extracts todos from OCR-read current chat messages using local heuristics. It specifies that results require manual confirmation and are not written to the task system. This distinguishes it from sibling tools like 'wechat_find_todos' (likely non-UI) and 'wechat_read_chat'.

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 some usage context: results are unconfirmed and not auto-committed. However, it does not explicitly state when to or not to use this tool, nor does it mention alternatives among siblings. The agent is left to infer appropriate use cases.

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?

Description adds context beyond annotations: it specifies the data source ('plaintext snapshot') and pagination behavior ('offset/limit'). Annotations already indicate read-only and idempotent, and description aligns with those. No contradictions.

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?

Single sentence with no filler. Front-loaded with the core action and resource, followed by key features. Every word is informative and 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 the output schema exists, the description does not need to explain return values. It covers source, filtering, and pagination. However, it omits any limitations (e.g., max results) or error conditions. Still, for a read-only list tool, it is largely 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 description coverage is 0%, so description must compensate. It explains '关键词' (keyword) for query, and 'offset/limit 分页' for pagination, covering three of four parameters. The 'response_format' parameter is not mentioned, leaving a gap.

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 '列出明文快照中的联系人和群聊' (list contacts and group chats in plaintext snapshot), specifying the resource (chats) and scope (snapshot-based). It distinguishes from sibling 'wechat_list_recent_chats' by emphasizing 'snapshot' rather than recent data.

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 siblings like wechat_list_recent_chats. The description only lists capabilities without stating use cases or 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?

Beyond annotations (readOnlyHint, destructiveHint, idempotentHint), the description discloses the OCR mechanism, UI-level reading, and guarantees no data modification beyond interface content. Full consistency with 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 extremely concise: two sentences front-loading the condition and method, with zero redundancy. Every sentence provides essential information.

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 existence of an output schema, return values are not needed. The description covers the tool's behavior well but lacks parameter documentation. Considering tool complexity (OCR, UI interaction), it is mostly 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 description coverage is 0%, yet the description provides no information about the 'limit' or 'response_format' parameters. The schema defines defaults and types, but the tool description adds no semantic value for parameters, leaving the agent to infer from names alone.

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 uses OCR to read recent chats from the current WeChat window when the database snapshot is not ready. It distinguishes itself from database-based siblings like wechat_list_chats and wechat_recent_messages by specifying the UI-based approach.

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 condition for use ('when the plaintext database snapshot is not yet ready'), implying that alternatives should be used otherwise. It does not name specific sibling tools but provides clear context for when this tool is appropriate.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the tool is safe and idempotent. The description adds context about filtering capabilities (time range, limit), which is helpful. No contradictions with 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 sentence that efficiently communicates the main purpose and key filtering options. It is front-loaded and contains 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 has an output schema and sibling tools, the description is minimal but adequate. It does not specify ordering, pagination, or behavior for missing chats. The presence of an output schema partially compensates for missing return value details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters. It explains the 'chat' parameter can accept various identifiers, and mentions ISO-8601 for time parameters and limit. However, it does not explain the 'response_format' parameter. This provides moderate semantic value but is incomplete.

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 the tool reads messages by contact nickname, remark, group name, or WeChat ID, with optional time and limit filters. This is specific about verb and resource, but it does not differentiate from sibling tools like wechat_search_messages or wechat_recent_messages.

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 such as wechat_search_messages or wechat_recent_messages. The description only explains what the tool does without contextual usage advice.

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=true. The description adds behavioral context: uses OCR, reads visible/scrollable content, may lack timestamps and sender identification. Does not contradict 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 with no filler, front-loading the core purpose and usage context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained. However, the description lacks parameter details entirely. For a complex OCR tool, this is a notable gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%. The tool description does not explain any of the four parameters (chat, limit, scroll_pages, response_format) beyond their names, leaving the agent uninformed about their meaning or usage.

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 uses OCR to read visible messages from a chat and positions it as a fallback when database snapshots are unavailable, distinguishing it from sibling tools like wechat_read_chat.

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 says it's a read-only fallback for when database snapshots are unavailable, and warns about missing precision. This guides the agent on when to use it vs 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?

Annotations already cover readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds the specific behavioral detail that messages are returned in reverse chronological order, which is useful but not extensive. It does not mention pagination, rate limits, or edge cases, but the annotations cover safety profiles.

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, front-loaded sentence with no wasted words. It efficiently conveys the core purpose and scope.

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 low complexity (3 optional params, no required) and existence of an output schema, the description is minimally adequate. However, it omits parameter details for limit and response_format, and lacks any usage context or examples. It meets the bare minimum but is not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only clarifies the 'chats' parameter by mentioning 'specified chats or all chats'. The 'limit' and 'response_format' parameters are not described at all, leaving their purpose unclear without external knowledge.

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 recent messages from specified chats or all chats in reverse chronological order. It uses a specific verb (返回) and resource (最近消息), and the scope is well-defined, distinguishing it from siblings like wechat_read_chat or wechat_search_messages.

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 no guidance on when to use this tool versus alternatives, such as wechat_search_messages for filtered queries or wechat_read_chat for a single chat's full history. No when-to-use or when-not-to-use conditions are mentioned.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, indicating a safe read operation. The description adds high-level features (time range, pagination, output format) but does not disclose additional behavioral details such as result ordering or limitations beyond default values.

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, well-structured sentence that front-loads the core action and scope. Every part 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 tool has 7 parameters, but the description only covers about half (time range, pagination, output format). With an output schema presumably present, return values are covered, but parameter coverage is incomplete, requiring the agent to rely on schema alone for missing aspects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It mentions time range, offset/limit, and output format corresponding to parameters, but fails to explain the 'query' or 'chats' parameters or provide any format/semantics details. This is insufficient given the parameter richness.

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 specifies that the tool searches text messages in all or specific chats, with support for time range, pagination, and output formats. This effectively distinguishes it from sibling tools like wechat_find_todos or wechat_recent_messages.

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. It only lists features, leaving the agent to infer appropriate usage without explicit context or 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 readOnlyHint, idempotentHint, destructiveHint. The description adds explicit statement that it does not read or return chat content, which is valuable beyond annotations. No contradictions.

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: first states action and components, second clarifies what it does not do. Both are concise and front-loaded. No 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?

Tool is simple with no parameters and has an output schema. Description covers what it checks and what it avoids, but could mention that it can be used as a prerequisite check before other WeChat tools. Still 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?

No parameters exist, so description does not need to add parameter details. Baseline for 0 parameters is 4. Description is sufficient.

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 title is in Chinese but clearly means 'Check local WeChat access status'. The description specifies read-only check of version, DB, key file, and snapshot readiness. It distinguishes from chat-reading tools by stating it does not read chat content. Clearly defines verb and resource, and differentiates from siblings.

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 this is a safe, non-invasive check but does not explicitly state when to use it vs alternatives like wechat_ui_diagnose or wechat_list_chats. No 'when to use' or '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?

The description adds behavioral details beyond annotations: it explains the tool decrypts to a read-only snapshot, does not modify source files, and does not send messages. This aligns with destructiveHint=false and idempotentHint=true. No contradictions with 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 two sentences in Chinese, efficient but missing parameter details. It front-loads the core purpose, but the structure could be improved by adding parameter explanations in a clear format.

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 complexity (two optional parameters, no enums, output schema exists), the description only covers high-level purpose and safety. It fails to document input parameters, leaving the agent underinformed. Output schema exists but is not referenced, reducing 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?

The input schema has two parameters (key_file, output_dir) with 0% description coverage, and the tool description does not explain their meaning or format. Without any parameter guidance, an agent cannot correctly supply values.

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: decrypting a WeChat database with a 64-bit hex key into a local read-only snapshot. It specifies the resource (db_storage) and verb (decrypt/create snapshot), and distinguishes from siblings by focusing on local snapshot creation rather than reading or searching.

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 a recommendation (exit WeChat before execution) and states safety (no modifications, no messages), but does not explicitly state when to use this tool versus alternatives like wechat_read_chat or wechat_list_chats. The guidance is present but not comprehensive.

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?

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses use of screenshots and OCR, non-persistence of data, and required permissions, adding valuable behavioral context without contradiction.

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 action and resource, and every sentence provides essential information 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?

For a parameterless diagnostic tool with existing output schema and annotations, the description covers prerequisites, behavior, and safety guarantees comprehensively.

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, so the baseline is 4. The description correctly omits parameter details as none exist.

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: diagnosing whether the WeChat main window is readable using macOS screenshot and local Vision OCR. It distinguishes itself from sibling tools like wechat_read_chat_ui by being a diagnostic pre-check.

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 mentions prerequisites (install ui optional dependency, grant screen recording permission) and assures no data is sent or saved. However, it does not explicitly guide when to use this tool versus alternatives like wechat_read_chat_ui.

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