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

No annotations are present, so the description must disclose all behavioral traits. It only says 'Add a sticker' without explaining side effects (e.g., overwriting, duplicates), authentication needs, or return value details beyond 'Status message'.

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 the one-sentence purpose and uses a clean Args/Returns format. It is reasonably concise, though the section detailing each parameter could be integrated into the main description.

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 5 parameters (3 required) and no annotations, the description provides basic parameter context but lacks details on output schema (only 'Status message') and fails to address typical edge cases or integration with sibling tools.

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 adds meaningful context to each parameter: 'name' is used in placeholders, 'md5' is a hash, 'tags' are comma-separated. This goes beyond the schema's type and title, though it could be more precise about 'file_path' and 'description'.

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 'Add a sticker to the library' with a specific verb and resource, and it distinguishes from sibling tools like 'wechat_list_stickers' and 'wechat_search_stickers' by focusing on addition.

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, nor are any prerequisites or conditions (e.g., file existence, permissions) 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?

With no annotations provided, the description must fully disclose behavior. It explains the core extraction and the optional file copy operation, which is good. However, it does not state whether the tool modifies chat history or any safety implications, leaving gaps for a critical operation.

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 efficient, with a clear one-liner followed by a structured Args section. It avoids unnecessary words, though it could be slightly more compact without losing clarity.

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 presence of an output schema (implied), the description adequately covers purpose, parameters, and return format. It lacks usage context and any discussion of scale or edge cases, but is mostly complete for the tool's complexity.

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 has 0% description coverage, so the description fully compensates by explaining each parameter in the Args block. Every parameter gets a clear, concise meaning beyond its name and type, including conditional logic for output_dir.

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 builds a sticker library from chat history, explaining what information is extracted. However, it does not explicitly differentiate from sibling tools like wechat_list_stickers or wechat_search_stickers, though the 'from chat history' phrase implies a different source.

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, nor does it mention any prerequisites or conditions. The 'Build sticker library' wording implies a specific use case, but no explicit when/when-not context is given.

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 is the sole source of behavioral information. It only says 'Search WeChat contacts' without describing how the search works, what filters apply, or any side 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 very short and front-loaded, but it sacrifices necessary detail. It is concise but not sufficiently informative.

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 0% schema coverage, 2 parameters, and an output schema, the description is incomplete. It fails to explain how to use the parameters or what the output contains.

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 adds no meaning for the two parameters (query, detail). The agent cannot infer their purpose or expected 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 'Search WeChat contacts', specifying verb and resource. However, it does not distinguish from sibling tools like wechat_search or wechat_members, missing an opportunity for differentiation.

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 wechat_search or wechat_members. The agent receives no context on appropriate usage scenarios.

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 exist, so the description carries full burden. It describes the main action and return format but does not disclose behavioral traits like read-only nature, required permissions (e.g., need prior chat history), rate limits, or side effects. Some context is provided but gaps remain.

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 front-loading. The first sentence captures the essence. The Args and Returns sections add needed detail, though the Returns line is somewhat redundant given an output schema exists. Still efficient overall.

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 three parameters and an output schema, the description covers the core functionality and parameter explanations. However, it lacks context like prerequisites (e.g., need active chat history) or connection to sibling tools (e.g., wechat_save_skill for saving the distilled skill). Adequate 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?

Schema description coverage is 0%, so the description compensates by explaining chat_names as comma-separated list, message_limit as max messages, and output_format as 'markdown' or 'json'. This adds meaning beyond the schema, though more detail (e.g., allowed values for output_format) could help.

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 distills personal communication style from chat history into a SKILL.md file. The verb 'distill' and resource 'personal communication style' are specific, and the tool is distinct from siblings like wechat_save_skill or wechat_search.

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 analyzing chat style to create a skill, but does not explicitly state when to use it versus alternatives (e.g., wechat_save_skill for saving already-created skills). No when-not-to or exclusions 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?

No annotations are provided, and the description only states 'list', implying a read operation but without explicit confirmation. No side effects, authentication needs, or rate limits are 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 a single, concise sentence that efficiently conveys the core action. However, it is so minimal that it sacrifices 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?

Given the tool has 2 parameters and an output schema exists, the description fails to explain parameter usage or provide actionable context. It is insufficient for an agent to invoke the tool correctly.

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

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

Schema coverage is 0%, meaning the description adds no meaning to the two parameters ('query', 'msg_type'). Their purpose, allowed values, and behavior are entirely unspecified.

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 'list' and the resource 'favorites/bookmarks', making the purpose unambiguous. However, it does not differentiate from sibling tools like 'wechat_search' or 'wechat_history', which could also list favorites.

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, nor any prerequisites or context. The agent is left to infer usage from the 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?

With no annotations, the description carries full burden. It discloses the action (get buffered messages) and the clear parameter's effect. While it could mention side effects or listener requirement, it is still fairly 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 very concise, using only two sentences for purpose and one for parameters/returns. No redundant information, 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 low complexity (1 parameter, no annotations, output schema exists), the description covers essential aspects. It could mention prerequisites like the listener must be running, but overall it is nearly 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%, but the description explains the 'clear' parameter's meaning and default, adding value over the raw schema. This compensates well for the lack of schema-level descriptions.

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 buffered messages from the listener, which is a specific verb-resource combination. However, it does not differentiate from sibling tools like wechat_new_messages or wechat_unread.

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_new_messages or wechat_history. It lacks context on prerequisites or typical 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?

No annotations provided, so description must disclose behavioral traits beyond basic purpose. Description only states it is a read operation, but does not mention whether it requires an active listener, whether messages are marked as read, or how media messages are handled. Minimal 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?

Single sentence, 8 words, front-loaded with key action. No unnecessary words, but could be slightly expanded to add parameter guidance without becoming overly long.

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

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

With 3 parameters, multiple siblings, and an output schema (likely complex), the description is too minimal. It does not explain what the output contains, how parameters affect results, or typical use cases. Incomplete for effective tool understanding.

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% (no descriptions in schema). Description does not clarify the meaning of 'limit' (e.g., max number of messages) or 'msg_type' (e.g., filter by message type). Only chat_name is implied by 'specific WeChat conversation'. Fails to compensate for missing schema descriptions.

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 'Read chat history from a specific WeChat conversation', specifying verb (read), resource (chat history), and context (specific conversation). It distinguishes from siblings like wechat_new_messages and wechat_search.

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?

Description implies usage for retrieving historical messages from a named chat, but provides no explicit guidance on when to use this tool versus alternatives like wechat_new_messages (recent) or wechat_unread (unread). No exclusions or prerequisites 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?

The description implies a read operation but does not elaborate on the exact return structure or behavioral traits. With no annotations, it should disclose more about what 'state' or 'statistics' entail.

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 terse sentences, front-loaded with purpose. No extraneous 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 zero parameters and an existing output schema, the description is adequate but could be more complete by specifying what 'state' or 'statistics' include.

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 the schema already covers that. The description adds 'Listener state and statistics' but does not clarify further. Baseline 4 is reduced due to lack of extra meaning.

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 'Get the current status of the message listener' with a specific verb and resource, distinguishing it from siblings like start_listener and stop_listener.

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 on when to use this tool versus alternatives like wechat_stats or checking messages. No exclusions or contexts 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?

With no annotations, description carries full burden. It only states the operation and return format, but does not disclose read-only nature, potential side effects, or any constraints.

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 sentences with no superfluous information. Purpose is 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 simple zero-parameter list operation, the description provides essential information. However, it could mention any pagination or limitations, but given no output schema shown, it is reasonably 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?

No parameters exist, so baseline is 4. Description adds value by specifying the output format ('JSON object with all stickers').

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 action 'List all stickers' and the resource 'in the library', which is specific and distinguishes from sibling tools like wechat_add_sticker or wechat_search_stickers.

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 on when to use this tool versus alternatives (e.g., wechat_search_stickers). Does not mention any usage 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?

With no annotations, the description carries the full burden but only states 'List members'. It does not disclose if the operation is read-only (safe to call), what format the members are returned in, or if there are requirements like authentication or group membership. This is insufficient for an agent to understand the tool's 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 single sentence is highly concise with no redundant words. However, it sacrifices substance for brevity; a slightly longer description could provide necessary details without losing conciseness.

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 a single required parameter, an output schema, and many siblings, the description is too minimal. It should at least clarify that the output is a list of member identifiers or profiles for the specified group. The current state leaves important gaps in understanding.

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 has 0% description coverage for the required parameter 'group_name', and the description adds no semantic meaning. The agent is left guessing whether 'group_name' refers to a display name, internal ID, or exact string match. No examples or format hints are given.

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 'List members of a WeChat group' clearly states the verb (list) and resource (members of a specific group), distinguishing it from siblings like wechat_contacts and wechat_sessions. However, it could be more explicit that it's for a single group identified by name.

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 vs siblings like wechat_contacts or wechat_search. There is no mention of prerequisites, such as being a member of the group, or alternatives for broader member queries.

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 but only mentions 'incremental' without explaining how 'last check' is tracked, whether messages are marked as read, or if a listener is required.

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, front-loaded sentence with no wasted words. It is efficient 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 zero-parameter tool with an output schema, the description is adequate but lacks details about the statefulness of 'last check' and the return format, which could affect 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 tool has zero parameters and schema coverage is 100%, so there is nothing for the description to add about parameters. Baseline 4 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 ('Get') and resource ('new WeChat messages'), adding the key qualifier 'since last check (incremental)' which differentiates it from siblings like wechat_history or wechat_unread.

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 siblings such as wechat_get_buffered_messages or wechat_unread, nor are there any prerequisites or contextual notes.

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 tool's behavior: parsing placeholders and returning a JSON array. It includes the expected input and output format. No annotations exist to contradict.

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, front-loaded with the main action, and includes a clear example. It uses separate sections for Args and Returns without unnecessary verbosity.

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, output schema), the description is largely complete. It could mention edge cases (e.g., no placeholders), but the example provides sufficient context 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 description adds significant meaning beyond the input schema for the 'text' parameter, explaining it as 'Text with sticker placeholders'. This compensates for the 0% 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 verb 'Parse' and the resource 'sticker placeholders from text', with an illustrative example. This distinguishes it from sibling tools like wechat_add_sticker or wechat_search_stickers.

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 the tool's purpose but lacks explicit guidance on when to use it versus alternatives. With many sibling tools, some context would be beneficial, but the example implies 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, so the description must fully disclose behavior. It describes the action and parameters but does not mention side effects like file overwriting, authentication requirements, or rate limits. The return value is mentioned only briefly.

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 well-structured with clear Args and Returns sections. Every sentence provides useful 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?

Given 4 parameters and an output schema, the description covers inputs and output comprehensively. It explains the purpose, parameters, and return value, making it complete for tool selection and 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%, but the description thoroughly explains all four parameters: chat_names, output_path, message_limit (with default 500), and output_format (with allowed values 'markdown' and 'json'). This adds significant meaning beyond the schema's bare titles.

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 ('Distill and save skill to file') and the resource ('Agent Skills compliant SKILL.md'). It distinguishes from the sibling 'wechat_distill_skill' by specifying that it saves to a file, not just distills.

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 saving distilled skills to a file, but does not explicitly state when to use this tool versus alternatives like 'wechat_distill_skill'. 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?

No annotations provided, and description lacks behavioral details such as whether search is global or per-chat, case sensitivity, or return format. Output schema exists but is not referenced.

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, no wasted words, but could be expanded with critical details. Acceptable conciseness for a simple search, but lacks 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?

With 3 parameters (1 required) and an output schema, the description is too minimal. It omits key context like filtering by chat_name and limiting results, which is necessary for proper 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 0% (no property descriptions). Description does not explain the meaning of 'keyword', 'limit', or 'chat_name' beyond their names. No added value.

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 action 'Search', resource 'WeChat messages', and method 'by keyword'. It is specific and distinct from sibling tools like wechat_history or wechat_new_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 on when to use this tool versus alternatives like wechat_history, wechat_new_messages, or wechat_get_buffered_messages. Agent must infer usage 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?

No annotations provided, and the description fails to disclose key behaviors such as search matching (exact vs. fuzzy), case sensitivity, or any side effects. Minimal transparency beyond the basic action.

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?

Concise with a clear Args/Returns structure. No unnecessary words, but slightly wastes space by restating obvious parameter names.

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 presence of an output schema (context indicates true), the description does not need to detail return format. However, it lacks details on search behavior and result ordering, which would improve completeness for a search tool.

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

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

Schema description coverage is 0%, and the description only repeats parameter names ('Search query', 'Maximum results to return') without adding constraints, formats, or examples. Does not compensate for the lack of schema descriptions.

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 'Search sticker library by name or description.' It uses a specific verb ('search') and resource ('sticker library'), and distinguishes from sibling tools like wechat_add_sticker and wechat_list_stickers.

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 on when to use this tool versus alternatives like wechat_list_stickers or other search tools. Missing explicit context for optimal 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 present, so the description must fully disclose behavior. It only says 'recent' without defining recency, and doesn't mention whether it's read-only, destructive, or any side 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 concise at one sentence, but it lacks necessary detail. It achieves brevity but at the cost of 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?

With an output schema present, the description doesn't explain the return format. Given the simplicity, it's somewhat complete but still misses key details like pagination or ordering.

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 has 0% description coverage; the only parameter 'limit' is not explained in the description. Despite being simple, the description adds no meaning beyond the schema's default value.

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 lists recent WeChat chat sessions or conversations. However, it doesn't differentiate from sibling tools like wechat_history or wechat_new_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_history for full history or wechat_new_messages for unread ones.

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 explains that it monitors database changes and buffers new messages, and returns a status message. However, it lacks details on background behavior, resource usage, or safety implications.

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 Args and Returns sections, front-loading the core purpose. It is slightly verbose but efficient without redundant 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?

With two parameters and an output schema, the description is fairly complete: it explains the tool's function, how to use parameters, and what to do next. Minor gaps on error handling or side effects are acceptable for a simple start-listener tool.

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

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

Schema description coverage is 0%, but the description adds meaning for both parameters: 'msg_dir' is explained with an example path and auto-detection, and 'interval' is described as polling interval in seconds with default 0.5. This compensates well for the schema 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?

The description clearly states 'Start listening for new WeChat messages' and explains the monitoring and buffering mechanism. It distinguishes itself from siblings like 'wechat_listener_status' and 'wechat_stop_listener' by indicating the retrieval process via 'wechat_get_buffered_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?

It specifies when to use the tool (starting a listener) and directs to 'wechat_get_buffered_messages' for retrieval. However, it does not explicitly state when not to use or compare to alternatives like 'wechat_new_messages', though the context is clear enough.

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 only says 'Get statistics', implying a read operation, but does not disclose behavioral traits like whether it aggregates data, respects time ranges, or has any limitations. With no annotations, the description should provide more behavioral details, which it fails to do.

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 short sentence, which is concise but under-specified. For a tool with three parameters and no annotations, more detail is needed. It sacrifices completeness for brevity.

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 three parameters, zero schema coverage, and no annotations, the description is severely incomplete. It does not explain what statistics are returned, time range behavior, or prerequisites. It is insufficient for an agent to use correctly.

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

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

The input schema has 0% description coverage, and the description adds no information about the parameters. It does not explain the purpose of start_time, end_time, or chat_name, or their expected formats. The agent gets no help beyond parameter 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 states 'Get statistics for a WeChat chat', which is a clear verb+resource. However, it is vague about what kind of statistics (e.g., message counts, frequency) and does not differentiate from siblings like wechat_history or wechat_members, which also provide chat-related 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 guidance is provided on when to use this tool versus alternatives such as wechat_history or wechat_members. The description lacks any context about appropriate scenarios or exclusions, leaving the agent without decision support.

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 must disclose behavioral traits. It only states the action and return value ('Status message'), but fails to mention what happens if the listener is not running, whether it blocks, or any side 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 extremely concise (two short sentences) and front-loaded with the primary action. 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 (no parameters, a single action) and the presence of an output schema, the description is nearly complete. However, it could mention prerequisites (e.g., listener must be active) for full clarity.

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 no parameters, and the schema coverage is 100%. The description does not need to add param info, and the baseline for zero parameters is 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 stops the message listener. The verb 'Stop' and resource 'message listener' are specific, and the purpose is easily distinguished from sibling tools like wechat_start_listener.

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 context of stopping a previously started listener is implied but not stated, leaving the agent to infer 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?

With no annotations, the description must disclose behavioral traits. It only states it 'shows' sessions, implying no mutation, but lacks details on whether viewing marks messages as read, authentication requirements, or other side 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 very concise with one sentence, but it is overly sparse and could benefit from additional context without becoming verbose. It is front-loaded but lacks 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?

Given the tool's simplicity and presence of an output schema, the description could be more complete. It fails to explain the parameter, usage context, or how it differs from similar sibling tools, making it less helpful for an AI agent.

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 adds no meaning to the 'limit' parameter. The description fails to compensate for the lack of schema documentation, leaving the agent uncertain about 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 'Show unread WeChat sessions' clearly states the action (show) and the specific resource (unread sessions), distinguishing it from sibling tools like `wechat_sessions` which likely shows all sessions.

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 `wechat_sessions` or `wechat_new_messages`. The description simply states what it does without usage context.

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