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

No annotations are provided, so the description carries the burden of behavioral disclosure. It mentions the rejection of 19 default-skills and targets missing files, but doesn't state whether it overwrites existing files, authentication requirements, or what happens on success or failure. This is adequate but not rich.

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, front-loaded sentences with no redundant wording. It efficiently communicates the action, scope, and a key exception.

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 (three well-documented params, no output schema, no annotations), the description covers the core purpose and usage boundaries well. The main gap is lack of detail about return values or side effects, but the scope is narrow enough that the description is still sufficiently 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 input schema already has 100% description coverage for all three parameters (skill, workspace, sourceWorkspace). The description only restates these as '指定 skill 名、目标工作区和来源工作区', adding no extra semantic detail 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 the action: '为跨工作区但缺少 .source.json 的 skill 补溯源文件' (supplement traceability files for cross-workspace skills missing .source.json). It specifies the exact resource (.source.json) and condition, distinguishing it from sibling tools like sync or 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?

It provides explicit usage context: cross-workspace skills missing .source.json, and an explicit exclusion: automatically rejects default-skills managed by workspace-watcher. However, it does not name alternative sibling tools to use instead, so it misses full 'when not to use' guidance.

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

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

With no annotations provided, the description carries full burden and excels: it discloses the tool's full scanning behavior, detection of erroneous .source.json files, exclusion of specific skills, and the exact three output groups (managed, unmanaged, orphans). This gives the agent a complete understanding of what to expect without needing 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 compact paragraph, front-loaded with the main purpose, then providing specific detection rules and output categories. Every sentence adds value, with no filler or 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?

Given the tool has no parameters and no output schema, the description fully covers the output by listing the three returned groups and their meanings. It also clarifies the detection logic and exclusions, making the tool's behavior complete for an agent to invoke 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 tool has zero parameters, so there are no parameter semantics to explain. The description adds no parameter details because none exist, which is appropriate. The baseline for 0 params is 4, and the description does not need to compensate for any schema gaps.

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 performs a 'full scan of all workspaces' and returns 'cross-workspace skill sync status', clearly identifying the verb (scan/check), resource (workspaces/skills), and specific output categories. This distinguishes it from siblings like 'sync', which likely performs the sync, while this tool checks status.

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 when to use this tool (to check sync status) but does not explicitly state when not to use it or name alternatives. It mentions it excludes 'default-skills managed watcher sync skills', which helps define scope, but lacks explicit 'use this instead of sync' guidance. However, the context of sibling tools provides some implied 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?

In the absence of annotations, the description thoroughly discloses behavioral traits: it notes the operation is irreversible ('不可逆操作'), details that it cleans up message files, attachments, and working directories, and explains the dry-run vs. actual deletion behavior based on the 'confirm' parameter. This fully informs the agent about side effects and safety.

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 three sentences, front-loaded with the primary purpose, followed by consequences and usage advice. While the sentences are somewhat long, every clause provides necessary information without redundancy. It strikes a good balance between detail and 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 that there is no output schema and no annotations, the description covers all essential aspects: what the tool does, the irreversible impact, the recommended timing, and the dry-run preview behavior. It even mentions what the dry-run lists (files/directories and their sizes). This is complete for a destructive tool with 3 parameters.

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

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

The input schema already has 100% coverage with descriptions for all parameters, including the 'confirm' safety gate. The description adds context about what gets deleted (files, attachments, directories) but does not introduce new parameter-specific semantics beyond what's in the schema. Therefore, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '删除指定的 Chat 对话或 Agent 会话' (Delete the specified Chat conversation or Agent session). It specifies both a concrete verb ('delete') and resource (session types), and differentiates it from sibling tools like list_sessions by focusing on deletion.

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 usage context: '建议在 Proma 关闭或切换到其他会话后操作' (recommended after Proma is closed or switched to another session). While it doesn't explicitly mention when not to use or alternatives, the guidance about avoiding conflicts with running processes is useful. Since there are no sibling delete tools, this is sufficient.

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 for behavioral disclosure. It adds a notable behavior: '自动拒绝 default-skills（workspace-watcher 管理的 19 个 skill）'. However, it does not state that the operation is read-only, what output to expect, or how errors (e.g., missing skill) are handled.

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

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

The description is compact, consisting of two sentences. It front-loads the purpose and then provides requirements and a key constraint, with no unnecessary words or 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 tool is moderately complex with two required parameters and no output schema. The description covers the main purpose and an important restriction, but it lacks details on the output format (e.g., how differences are presented) and does not clarify prerequisites like workspace existence. Given the absence of an output schema, this leaves some gaps for the user.

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

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

The input schema already describes both parameters fully (skill name and workspace slug with examples). The description only repeats the requirement to specify them, adding no new semantic meaning beyond the schema. With 100% schema coverage, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: '对比母版和某个子版 skill 的完整目录差异（文件级 + 行级）' (compare complete directory differences between master and sub-version skill, file-level + line-level). It is specific with a verb and resource, but it does not explicitly differentiate from sibling tools like 'check' or 'sync'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions required parameters ('需指定 skill 名和目标工作区 slug') and the automatic rejection of default-skills, but it does not provide guidance on when to use this tool versus alternatives. There is no explicit 'use this when...' or mention of preferable scenarios compared to siblings.

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 several behavioral traits: automatic exclusion of 19 watcher-sync skills, the return fields (name, description, current group, body preview), and default workspace scanning. This adds meaningful context beyond the bare parameters.

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, each earning its place: first states the main function and purpose, second covers exclusions and return/defaults. No fluff, front-loaded with the essential action.

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 listing tool with no output schema, the description covers the purpose, the output fields, default workspace, and a key exclusion. It omits potential edge cases (e.g., empty workspace, errors) but is otherwise complete for agent decision-making.

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 only parameter (workspace) has full schema description coverage, including default and dynamic discovery. The description reiterates the default but adds no syntax or value details beyond the schema, so the schema does the heavy lifting (baseline 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 states the tool lists group status and content summaries for all skills in a workspace, with a specific verb ('列出') and resource. It distinguishes from group_set by noting it is for AI analysis before assigning groups, and additionally specifies auto-exclusion of certain skills.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context: use to analyze skills before automatically assigning groups, and defaults to the default workspace. It does not explicitly name alternative tools or when not to use it, but the intended usage is evident from the '供 AI 分析后自动分配 group' phrase.

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

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

With no annotations provided, the description carries the full burden and discloses key behavioral traits: batch operation, replacement of existing groups, addition of new ones, and automatic rejection of default-skills. It doesn't cover permissions or failure modes, but the essential side effects are well communicated.

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 exceptionally concise: three sentences that front-load the primary action, with each sentence providing distinct, valuable information—operation, batch behavior, and the rejection rule.

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 two-parameter tool with no output schema, the description covers the core functionality, important edge cases (default-skills rejection), and behavioral semantics. No critical operational aspects are missing for an agent to invoke it 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 100%, but the description adds meaning beyond the schema field names: it specifies batch semantics for the 'groups' parameter and explains the replace/insert behavior. This enriches the understanding of how the parameters are used.

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 a specific action and resource: 'Writes the group field in SKILL.md frontmatter' and describes batch mapping. It distinguishes from sibling group_list by indicating a mutation operation versus a read 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?

It provides clear context for use: batch update of skill-to-group mappings with replace-or-insert semantics. It doesn't explicitly name alternatives, but the action's scope is unambiguous and the rejection of default-skills serves as an implicit when-not-to-use signal.

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 carry the full burden of behavioral disclosure. The verb '查看' (view) implies a read-only operation, but the description does not explicitly state that there are no side effects, what permissions are required, or whether the tool modifies anything. It does disclose the output content (workspace existence, hash, file list, parent/child), but omits other behavioral traits such as error conditions or 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 a single, concise sentence that front-loads the primary action and resource, followed by a compact list of the included aspects. Every part is necessary and informative; there is no fluff, repetition, or tangential detail. It is well-structured for quick comprehension.

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 provides a reasonably complete picture of what the tool returns. It names the key output categories. However, it does not describe the return format, how the data is structured, or potential error scenarios, which would be helpful since there is no output schema. Still, it covers the essential purpose well.

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% because the single parameter 'skill' is described as 'Skill 名称（目录名）'. The description adds only the word '单个' (single), which is redundant. Since the schema already explains the parameter fully, the description provides minimal additional semantic value beyond what is structured.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: '查看单个 skill 的完整溯源视图' (view the complete traceability view of a single skill). It specifies the resource (a single skill) and the verb (view), and lists the specific aspects covered (workspace existence, hash, file list, parent/child relationships). This distinguishes it from sibling tools like sync or check by focusing on detailed traceability information.

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: use this tool when you need a complete traceability view of a skill. However, it provides no explicit guidance on when to use it versus alternatives, no exclusions, and no mention of prerequisites or context. It falls short of explicitly naming when not to use it or which sibling tool might be better suited for different 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 are provided, so the description carries the burden. It discloses the return metadata fields and the filtering capability. Although it does not explicitly state side effects or read-only nature, as a listing operation this is largely implied and adequately 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?

Three short sentences with no filler. The purpose, return metadata, and filter option are all covered efficiently, making it easy for an agent to quickly understand the tool.

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 list tool with one optional parameter, the description is quite complete. It names return metadata fields and filter capabilities, which is sufficient given no output schema. It could mention pagination or result format, but it is not critical here.

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 fully documents the single 'type' parameter with enum values and descriptions, so the description adds little beyond a redundant mention of filtering. Baseline of 3 is appropriate when schema coverage is 100%.

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 explicitly states the tool lists all Chat conversations and Agent sessions, uses the specific verb '列出' (list) with a clear resource, and mentions returned metadata (title, time, archive status, workspace). It clearly distinguishes from sibling tools by focusing on listing rather than deletion or other operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates this is for listing sessions and optionally filtering by the type parameter. It does not explicitly name alternatives or exclusions, but the context is unambiguous given the sibling tools include delete_session and group_list, making the intended use clear.

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

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

With no annotations, the description carries the burden of behavioral disclosure. The verbs '扫描' (scan) and '返回' (return) clearly imply a read-only diagnostic operation with no side effects. It does not mention failure modes or permissions, but for a simple scan tool this is adequate.

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

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

Two concise sentences: the first states the action and result, the second explains the purpose and target invariant. Every word adds value, no filler.

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

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

For a zero-parameter, no-output-schema tool, the description is sufficient: it explains what is scanned, what is returned, and why. The only slight gap is that 'server collection' is not precisely defined, but this is minor for such a simple tool.

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

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

The tool has zero parameters, so the baseline is 4. There is nothing for the description to explain about parameters, and the schema fully covers the (empty) parameter set.

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 scans mcp.json across all workspaces and returns the server collection plus missing servers per workspace. It uses a specific verb ('扫描') and resource ('所有工作区的 mcp.json'), and the goal of config consistency distinguishes it from sibling tools like 'sync'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context: it is used to keep MCP configuration consistent across workspaces and explains the expected invariant ('each server either exists everywhere or only where needed'). It does not explicitly name alternative tools or exclusion scenarios, so it stops short of a 5.

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

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It reveals important behaviors: backing up the child version to .sync-backup/ before overwriting, updating .source.json, requiring sourceWorkspace on first distribution, and rejecting default-skills. This is rich, actionable behavioral context beyond the schema.

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

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

The description is compact and front-loaded, using four sentences to convey purpose, behavior, parameter conditionality, and exclusions. Every sentence earns its place with no redundancy or filler.

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

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

Given the tool's moderate complexity, no output schema, and helpful parameter schema, the description covers all essential aspects: what it does, how it behaves, when to use the optional parameter, and what it rejects. It is complete enough for an agent to correctly invoke the 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 coverage is 100%, so the baseline is 3. The description adds value by clarifying that 'skill' is the directory name and 'workspaces' are child workspace slugs, and it reinforces the conditional requirement of sourceWorkspace for first-time distribution. This exceeds the baseline by providing operational context not fully explicit 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 a specific action: pushing an entire skill directory from a parent workspace to one or more child workspaces. It distinguishes this tool from siblings by focusing on the sync/push operation and explicitly mentioning the backup and overwrite 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?

The description provides clear usage context: it specifies the sourceWorkspace parameter is required for first-time distribution, and it notes automatic rejection of default-skills. It does not explicitly name alternative tools or exclusion cases, but the context is sufficient for typical use.

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