Skill of Skills

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

No annotations provided. Description only adds ordering behavior and input constraints (2-5, slug). Lacks details on auth, side effects, rate limits, or return format beyond referring to get_skill.

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, front-loaded sentence with no waste. However, it could include more guidance on slug format or output structure 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?

Moderate complexity with 1 required param and no output schema. Description covers input constraints and behavior but references get_skill for fields, assuming prior knowledge. Lacks explicit return structure details.

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

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

Schema coverage is 0%; description only says 'by slug' without explaining slug format or how slugs relate to tools. The schema pattern and length are not clarified, so added value is minimal.

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 'Side-by-side quality profiles for 2–5 tools by slug' and specifies behavior like 'ordering follows the request, not rank'. It distinguishes from siblings by referencing get_skill's fields and emphasizing 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?

Implies use when comparing 2-5 tools, but no explicit when-not or alternatives. Sibling tools (get_skill, list_collections) are not contrasted, and no guidance on when to choose this over others.

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 provides good behavioral context: it is public, k-anonymous, aggregates from at least 5 distinct sessions, and is sourced from the directory. This adds value beyond what would be in annotations.

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

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

The description is two sentences, front-loaded with key attributes (public, k-anonymous, aggregates). Every sentence serves a purpose, no waste.

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?

All critical aspects are covered: source, aggregation method, anonymity guarantee. However, it does not describe the output format (e.g., whether it returns a list or object), which would be helpful given no output schema.

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 zero parameters, so baseline is 4. The description adds meaning by explaining the output content, which is sufficient for this parameter-free tool.

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 provides a public, k-anonymous demand signal including trending searches, most-saved, and most-installed tools. It distinguishes itself from sibling tools like compare_tools or search_skills by focusing on aggregated demand data.

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

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

The description implies use for retrieving aggregated popularity data but does not explicitly state when to use it versus siblings or when not to use it. No alternatives or exclusions are mentioned.

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

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

The description discloses that tools are quality-ranked and that high/critical-risk tools are excluded unless 'include_high_risk' is set. However, it omits pagination behavior (limit parameter), ordering details, and response structure in absence of annotations or output 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?

Two short sentences cover the core functionality and a key behavioral condition with no waste. Every sentence is essential.

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 three parameters, no output schema, and no annotations, the description leaves major gaps: it doesn't explain the purpose of 'slug' or 'limit', nor what the response contains beyond 'tools'. A more complete description should describe each parameter and the format of the returned tools list.

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 fails to explain any parameter. It indirectly mentions 'include_high_risk' but does not clarify 'slug' (which selects the collection) or 'limit' (controls count). Agents cannot infer parameter meanings.

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 returns 'Quality-ranked tools inside one curated collection,' clearly indicating it retrieves a set of tools from a specific collection. It implicitly distinguishes from sibling 'list_collections' by focusing on content within a single collection, but could be more explicit about the verb.

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 vs alternatives like 'list_collections' or 'get_skill'. The description only mentions a behavioral rule about risk filtering, not usage 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?

With no annotations, the description carries the full burden. It discloses that any active tool is returned regardless of risk, which is a key behavioral trait. However, it does not mention idempotency, safety, or other typical behavioral aspects.

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

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

The description is two sentences, with no filler. The first sentence lists contents, the second adds behavioral nuance. Every sentence is essential.

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 adequately covers the return contents (score breakdown, risk, etc.) and the behavior (no risk filter). Could include a note on response format but is sufficient.

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' is described with context: 'slugs come from search_skills / get_collection'. This adds meaning beyond the schema pattern/constraints, guiding the agent on valid 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 states 'Full quality profile for one tool by slug' and lists the contents, making the purpose clear. It mentions slugs come from other tools, but does not explicitly differentiate from siblings like compare_tools or search_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?

The description implies usage (use after obtaining a slug) and mentions that risk is not a filter, but does not explicitly state when to use this tool over siblings or provide negative examples.

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, but description adequately describes a read-only listing operation. Provides examples and context about collections.

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 that efficiently convey purpose and usage. No unnecessary content.

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

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

For a parameterless, no-output-schema tool, description fully covers what the tool does and how it relates to 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?

No parameters, so schema covarge is 100%. Description adds context about what is listed without needing parameter details.

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?

Clearly states it lists curated buyer-intent collections, with examples. Distinguishes from sibling 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?

Explicitly tells when to use (list collections) and when not (use get_collection for tools inside one). Provides clear 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?

With no annotations provided, the description carries full responsibility for behavioral disclosure. It explains that results are filtered by default (quality and risk) and that scores are evidence, not endorsements. This adds context beyond the schema, though it omits details like read-only nature, pagination, or response structure. Still, it provides useful behavioral traits.

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 long, front-loading the core purpose and then providing key behavioral details. Every sentence adds value: the first defines scope, the second explains ranking, the third specifies default filters. No fluff or repetition.

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 lack of an output schema and annotations, the description could be more complete. It does not describe the return format (e.g., fields, pagination, total count) or mention any rate limits. While it covers the search behavior and defaults, it leaves gaps that an agent would need to infer or test.

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 80%, so the schema already documents most parameters. The description adds overall context about ranking and default filtering, which indirectly clarifies the query parameter's role. However, it does not detail individual parameter usage beyond what the schema provides. For the 'limit' and 'platform' parameters, no extra meaning is added. Score at baseline.

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 the Skill of Skills directory, specifying the types of resources included (AI coding skills, plugins, MCP servers across multiple platforms). It uses a specific verb-resource pair ('search' over 'Skill of Skills directory') and naturally distinguishes itself from sibling tools like get_collection or compare_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 provides explicit context about default filters (quality ≥ 40, risk below high) and ranking (quality-first, not popularity). While it doesn't explicitly state when not to use this tool or name alternatives, it gives clear guidance on when the tool will return results, aiding the agent in understanding invocation triggers.

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