Skill of Skills

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

With no annotations, the description adds behavioral details: 'ordering follows the request, not rank' and 'Same fields as get_skill'. However, it omits other traits like idempotency, rate limits, or authorization needs.

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: first states the core purpose, second adds relevant details about fields and ordering. No redundancy or 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 low complexity (1 param, no output schema), the description is fairly complete. It explains what fields are returned (same as get_skill) and ordering behavior, though 'quality profiles' is slightly vague.

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%, so description must compensate. It explains the 'slugs' parameter is used for identifying tools via slug and enforces a 2-5 count. This adds meaning beyond the schema's pattern and length constraints.

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

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

The description clearly states 'Side-by-side quality profiles for 2–5 tools by slug', which specifies the action (compare), resource (quality profiles of tools), and scope (by slug, 2-5). It also distinguishes from sibling 'get_skill' by implying multiple tools.

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 comparing multiple tools via slugs, and references 'get_skill' for field consistency, but does not explicitly state when to use this tool versus alternatives like 'search_skills' or 'get_collection'.

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 carries the burden of behavioral disclosure. It reveals that the data is public, k-anonymous, aggregated, and privacy-protected (≥5 sessions). No contradictions or omissions.

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, front-loaded with key information, no wasted words. Highly efficient and clear.

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 no output schema, the description sufficiently explains what the tool returns (trending searches, most-saved, most-installed). It covers the essential aspects for a zero-parameter tool without gaps.

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

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

There are no parameters (schema coverage 100%), so baseline is 4. The description adds no parameter info, but none is needed since the tool takes no inputs.

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 provides a 'demand signal' (trending, most-saved, most-installed) from the directory, using specific verbs and resource. It distinguishes itself from sibling tools like compare_tools, get_collection, etc., which serve different purposes.

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

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

The description explicitly states 'Aggregates only' and the anonymity threshold (≥5 sessions), giving context on when to use. It does not explicitly exclude other scenarios or mention alternatives, but the purpose 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?

Without annotations, description discloses the risk-based exclusion behavior. However, it omits other behaviors like ordering, pagination, 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?

Two concise sentences front-load the core action and key behavioral condition, with no wasted words.

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

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

For a tool with 3 params and no output schema, the description lacks return structure, error cases, and full behavioral context, leaving significant unknowns for an 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 descriptions are absent (0% coverage). Description explains include_high_risk partially, but slug enum values and limit have no added meaning, failing to compensate for low 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?

Description clearly states the tool retrieves quality-ranked tools from a curated collection, with a specific filtering mechanism. It distinguishes from siblings like list_collections and get_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 usage for retrieving collection contents, with context on risk filtering. No explicit exclusions or alternatives, but the role is clear given sibling names.

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. It discloses the returned components (score breakdown, structural signals, risk level/reasons, platforms, repo link) and states that any active tool is returned regardless of risk. This provides adequate transparency for a read 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 two sentences with no wasted words. The first sentence efficiently lists the content, and the second sentence adds an important clarification about risk handling. It is appropriately sized for the tool's simplicity.

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 one parameter and no output schema, the description covers all essential aspects: what the tool returns (key components), where to get the input (slugs from sibling tools), and behavioral nuance (risk is not a filter). This is complete for an agent to select and 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?

The single parameter 'slug' has no description in the schema (0% coverage). The description adds meaning by explaining that slugs come from search_skills/get_collection, which helps the agent understand how to obtain a valid 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 uses a specific verb 'get' and resource 'skill profile', and lists the content (score breakdown, structural signals, risk level, platforms, repo link). It distinguishes from siblings by noting that slugs come from search_skills/get_collection.

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

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

The description explicitly states when to use: for a full quality profile by slug, including risk assessment. It clarifies that risk is part of the answer, not a filter. It implies slugs are obtained from search_skills/get_collection but does not explicitly list exclusions or alternatives.

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

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

No annotations are provided, so the description carries the burden. It mentions 'curated' and gives examples, implying a read operation that returns a list. However, it does not disclose authentication requirements, rate limits, or whether the list is exhaustive. For a simple zero-param tool, this is minimally adequate but lacks depth.

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: first states purpose with examples, second provides usage guidance to a sibling. No filler or wasted words. Excellent structure.

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

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

Given the tool has no parameters, no output schema, and no annotations, the description covers what it returns (curated collections) and links to the related tool for deeper exploration. It is sufficient for an agent to understand and select the tool, though it could optionally mention if the list is ordered or filterable.

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 no parameters, making schema description coverage trivially 100%. The description adds no extra parameter info, but since there are none, no compensation is needed. Baseline score of 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 tool lists 'curated buyer-intent collections' and provides examples, specifying the verb and resource. It distinguishes from sibling get_collection by indicating list vs. detailed view.

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 directs to use get_collection for ranked tools inside a collection, providing clear context for when to use this tool vs. the sibling. No further alternatives or exclusions are mentioned, but the guidance 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?

No annotations provided, so the description carries full burden. It discloses sorting mechanism, default filtering, and the nature of scores (evidence, not endorsements). No mention of side effects, but as a search tool, it's likely read-only.

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, front-loaded with the core purpose, no redundant information. Every sentence adds value.

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 purpose, defaults, ranking. Lacks description of return format (no output schema), and does not explicitly differentiate from siblings, but given simplicity of tool, it is largely complete.

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

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

Schema coverage is 80%, so baseline is 3. The description adds context about default quality floor and risk filtering, enriching understanding of 'min_tier' and 'include_high_risk' parameters beyond their 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 it performs full-text search over a specific directory (Skill of Skills) covering multiple platforms. It distinguishes from sibling tools like 'get_skill' (retrieves a single skill) and 'compare_tools' (comparison).

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

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

Provides clear context: results ranked by quality-first score, default filters (quality ≥40, risk below high). Lacks explicit exclusions or when to use alternatives, but the context is sufficient.

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