AI Skill Directory

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

Annotations already declare readOnlyHint, idempotentHint and a closed world, so safety is covered. The description adds real value by naming what the returned payload is (SKILL.md text, prompt text, or MCP config), which matters since there is no 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?

One sentence, front-loaded with the action and resource, with no redundant or filler clauses.

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 one-param read tool with full schema coverage and annotations, the description covers the essentials and even compensates for the missing output schema by describing return content. It omits error behavior for an unknown slug, a minor 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?

There is a single parameter at 100% schema coverage, and the schema already explains that the slug comes from search_skills. The description only restates 'by slug', so baseline 3 applies.

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?

States a specific verb (fetch) and resource (skill) with the identifying key (slug) plus the content variants returned (SKILL.md, prompt text, MCP config). This is clearly distinguishable from search_skills and list_categories, though it does not name the siblings explicitly.

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 clause 'so the agent can use or install it' hints at the downstream use case, but there is no explicit when-to-use/when-not guidance or pointer to search_skills for discovering a slug. Usage is implied rather than stated.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the description need not restate safety. It adds that slugs are returned alongside section names, but says nothing about ordering, whether the list is static, or the response shape beyond that one clause.

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 filler. Every word (resource, scope, returned field) earns its place.

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 no parameters and no output schema, the description needs to carry the return-value burden, and it does minimally by mentioning slugs. It stops short of describing the item structure (name/slug format, ordering), so it is nearly 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; schema coverage is 100% as well. Baseline 4 applies.

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 a specific verb (List) and resource (sections of the AI Skill Directory) and indicates the payload carries slugs. It is clearly different from get_skill/search_skills by resource, but it never names a sibling or explicitly contrasts the scope.

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 when-to-use or when-not-to-use guidance is given. The intent (enumerate categories before drilling into skills or searching) is only implied by the resource name and the presence of search_skills/get_skill 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?

Annotations already declare readOnly, idempotent and closed-world, so safety behavior is covered. The description adds genuinely new information that annotations cannot convey: the result payload is a list of slugs rather than full records. It says nothing about empty results, ranking or the 50-result cap, but for a lookup tool this is solid.

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, zero filler. The purpose leads and the follow-up action is second, matching the order an agent needs them.

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 no output schema, the description correctly compensates by stating what comes back and how to use it. What remains unstated is minor for a search tool: whether results are ranked, what an empty response means, and pagination past the limit cap.

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 all four parameters are documented in the schema, including the enum and the note that category comes from list_categories. The description adds no semantics beyond that, which is the baseline for a fully documented 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?

States a specific verb (search) plus the corpus being searched and the enumerated entry types (skills, prompts, MCP servers, rules). It also names the sibling it feeds into (get_skill), so an agent can place it in the workflow without opening either schema.

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 establishes the two-step pattern explicitly: search here, then pass the returned slugs to get_skill. It does not state when not to use this tool (e.g., when a slug is already known), but the positive routing is unambiguous.

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