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

With no annotations present, the description carries the behavioral burden. It discloses that remote bytes are fetched and validated before storage, explains profile sync behavior, and notes how local provenance is handled. It could go further by covering return values or idempotency, but the core side effects are clear.

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 dense but organized by source type and front-loaded with the main purpose. Every sentence adds operational detail, though the reference to 'CLI add-local --source' adds a mild assumption that could be clarified.

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 9 parameters, nested objects, no output schema, and no annotations, so the description has a heavy burden. It covers the main remote and local branches well, but omits return behavior, error cases, and several unexplained parameters, leaving the definition only partially 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 must compensate. It meaningfully explains source, identifier, skill_dir, target_agents, and sync_profiles. However, verbose, version, profile_roots, and discover_profile_roots are left entirely unexplained, leaving notable gaps for an agent.

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

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

The description opens with a clear verb and resource: 'Add a known skill from a source.' It then distinguishes itself from propose_skill by explicitly stating that caller-authored SKILL.md bytes should use propose_skill, not add_skill, which helps an agent pick the right tool among 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 gives concrete when-to-use guidance per source type: remote sources need source plus identifier, local bundles need source: 'local' and skill_dir. It also explains profile sync conditions and points to propose_skill as the correct alternative for caller-authored SKILL.md bytes.

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 validation, dedup, agents filling, resource inference, and profile sync. However, it does not mention side effects (e.g., whether source files are modified), authentication needs, or error handling, leaving gaps.

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 paragraph with no wasted words. It front-loads the core action and adds details sequentially. Could be slightly improved with bullet points for clarity, but overall efficient.

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

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

Given the tool complexity (7 params, no output schema, no annotations), the description provides adequate but not complete context. It explains main behavior and a few parameters, but leaves many details about error handling, prerequisites, and return behavior implicit.

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

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

With 0% schema description coverage, the description must compensate. It explains source_dir, agents, and verbose, adding meaningful context. However, four parameters (allow_synthesized_frontmatter, sync_profiles, profile_roots, discover_profile_roots) remain unexplained, so coverage is only partial.

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 (import) and resource (immediate child directories containing SKILL.md). It also distinguishes behavior from sibling propose_skill by referencing it, but does not explicitly differentiate from other siblings like add_skill or update_skill.

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 explicit guidance on when to use bulk_import versus alternative tools. It mentions 'like propose_skill' but lacks any when-to-use or when-not-to-use instructions, 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 covers main behaviors: hash comparison, handling of sources, and reporting of unchecked inline skills. Does not explicitly state it is read-only but implies it.

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 focused sentences, front-loaded with purpose, every sentence adds value, 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?

Covers drift detection mechanism and special case for inline skills, but lacks output format details (no output schema), leaving the return structure unclear.

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 optional 'skill' parameter is not explained in the description, leaving ambiguity about whether it filters or specifies which skills to check, despite 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 tool detects upstream drift for skills by comparing content hashes, distinguishing it from sibling tools like update_skill or delete_skill.

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?

Implies use before updating but lacks explicit when-to-use or when-not-to-use guidance relative to siblings like update_skill or propose_skill.

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 of behavioral disclosure, and it does so thoroughly. It explains default host root discovery, the pruning of managed consumer links, the opt-out via discover_profile_roots: false, and the additional removal of vault-local transforms. This gives an agent a strong mental model of side effects beyond the basic delete 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?

The description is three sentences with no filler: the primary action and immediate effect come first, the configurable discovery behavior follows, and the additional transform removal closes it out. Every sentence earns its place and the structure is easy to parse.

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 destructive tool with no annotations and no output schema, the description covers the key behavioral surfaces well: what is deleted, what is refreshed, what is pruned, and how to opt out. The main missing piece is a clearer explanation of the profile_roots parameter's shape and purpose, which prevents this from being fully complete for advanced 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 description coverage is 0%, so the description must compensate. It adds useful meaning for discover_profile_roots by explaining its default and the opt-out behavior, and 'name' is self-evident. However, the profile_roots object parameter is never explicitly explained or mapped to the 'host skill roots' concept, leaving a significant gap for an optional but non-trivial 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 opens with a specific verb and resource: 'Delete an installed skill from the vault', and immediately distinguishes this from all sibling tools whose names describe add/get/update/propose actions. The secondary effect of refreshing generated profiles is also stated, so an agent knows exactly what action is performed.

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 purpose is unambiguous: deleting a skill is clearly the inverse of add_skill or update_skill, so the usage context is clear from the first sentence. It does not explicitly name alternatives or exclusion conditions, but the tool's destructive role among these siblings is obvious and the description gives actionable context for when to use it.

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 description carries full burden. It discloses that query returns best match and alternates, include_resources controls inlining, and agent applies AutoVault transforms. However, it does not mention behavior if both name and query are provided, or error handling.

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

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

Three sentences cover the main functionality efficiently. The structure mixes parameter explanations within usage, but no word wasted. Could be more organized by grouping parameter descriptions.

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 0% schema description, no output schema, and no annotations, the description covers the two modes and most parameters. However, it misses the top_k parameter, does not describe the output format, and lacks error behavior. Adequate but not 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 has 0% description coverage, so description must compensate. It explains name, query, include_resources, and agent clearly, but omits top_k completely despite its exclusiveMinimum and maximum constraints. 4 out of 5 parameters are described, but the missing one is 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 the verb (Find/load) and resource (installed skills). It distinguishes between exact match by name and search by query, and mentions optional parameters. Among siblings focused on mutation, it stands out as the retrieval tool.

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

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

The description implies when to use name vs query, but lacks explicit guidance on when to use this tool over siblings like propose_skill or delete_skill. No prerequisites or when-not conditions 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?

With no annotations, the description fully discloses that the tool runs validation, security scan, capability cross-check, and three-tier deduplication. This reveals significant behavioral traits beyond a simple save, such as potential rejection or merging. It does not, however, specify error behavior or what happens on duplicate detection.

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 four sentences, with the primary action and key checks in the first sentence. Every sentence adds value, and the structure is front-loaded for quick understanding.

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

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

Given the complexity (6 parameters, no output schema), the description lacks parameter explanations and output details. While core usage is clear, an agent cannot reliably construct calls without parameter semantics or understand return values, which is a significant 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 coverage is 0%, and the description explains none of the 6 parameters beyond 'SKILL.md' for skill_md. Terms like resources, source_session, and allow_synthesized_frontmatter remain undefined, leaving the agent without guidance on how to populate them.

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

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

The description clearly states the tool submits a SKILL.md to AutoVault and lists the specific checks performed (validation, security scan, etc.). It distinguishes itself from alternatives by explicitly recommending it over writing skill files directly to disk, implying it is for new skills, contrasting with siblings like update_skill.

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

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

The description explicitly says to use when saving a conversationally created skill or after drafting one for reuse. It also advises preferring this over direct file writes. However, it does not explicitly exclude use cases for updating existing skills, where update_skill might be more 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?

No annotations exist, so the description carries full burden. It discloses key behaviors: refreshing source with only name, rejecting mismatched frontmatter, default compact sync counts, and the verbose option. It does not cover side effects or auth requirements, but for an update operation the transparency is relatively high.

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 paragraph covering numerous update modes and flags without excessive verbosity. It front-loads the main purpose. Each clause adds value, but the density could be slightly improved by splitting into bullet points for easier scanning.

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 12 parameters, nested objects, no output schema, the description is fairly complete for the main use cases. However, details on resources, sync profiles, profile_roots, and discover_profile_roots are missing, which may leave agents uncertain about those 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?

Schema description coverage is 0%, so the description adds meaning to many parameters (name, source, identifier, skill_dir, skill_md, reuse_existing_resources, verbose). However, parameters like resources, sync_profiles, profile_roots, discover_profile_roots, and version are not explained. The coverage is about 7/12 (58%), providing moderate compensation but with 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 clearly states 'Update an installed skill' and distinguishes various update modes (refresh, new source, local, inline). It is specific about the verb and resource, and the sibling tools (add_skill, delete_skill) provide contrast, making the purpose unambiguous.

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

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

The description provides explicit guidance on when to use different parameter combinations (e.g., just name for refresh, source+identifier for new source, etc.) and flags like verbose and reuse_existing_resources. However, it does not explicitly contrast when to use this tool over siblings like add_skill, but the update context is implied.

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