Recommend OpenCode skills

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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds real context beyond them: only metadata is read, never the skill body, which tells the agent the call is cheap and avoids side effects on skill content. It also discloses the return payload shape (path plus reason). It stops short of explaining ranking/threshold behavior or what happens when nothing clears the bar.

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, front-loaded with the action and result, with each sentence adding a distinct fact (what it does, what it reads, what the caller must still do). No filler 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?

For a read-only ranking tool with a nested options object and no output schema, the definition covers purpose and read scope but leaves the tuning parameters unexplained and gives no sense of result ordering count or empty-result behavior. Adequate, but an agent would still be guessing about threshold semantics.

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 67%, so the description's baseline is a 3. It reinforces that ranking happens "against a task" (pointing at user_query) and that recommendations are drawn from skills "discovered on disk," which loosely frames available_skills as a restriction. It says nothing about the nested threshold or max_recommendations options, which are the least documented parameters.

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?

"Rank the skills discovered on disk against a task and return the ones worth loading" names a specific verb (rank), the resource (discovered skills), and the matching criterion (a task), plus what comes back (SKILL.md path and reason). It is clearly distinguishable from siblings like systemone_get_catalog or systemone_refresh_catalog, which manage rather than rank the catalog.

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 agent still loads the skill itself" implies the two-step workflow: recommend here, then load separately, which is useful guidance. However, there is no statement of when to prefer this over systemone_analyze_task or systemone_decide_tools, and no exclusion or precondition guidance.

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