find_skill

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

There are no annotations, so the description carries full burden. It describes the 3-layer loading behavior and progressive detail levels, which is useful behavioral context. However, it does not disclose return structure, output format, or any side effects. The description does disclose the legacy migration (ecosystem_recipes content moved into integration category), which is helpful context beyond what schema provides.

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 well-structured with clear layer breakdowns and a final note about the integration category. Each sentence adds value and the progression is logical. It's slightly long but all content is load-bearing — the layer descriptions directly help the agent decide how to call the tool.

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 an output schema and 100% parameter coverage, the description's job is to explain the multi-level behavior, which it does thoroughly. The 3-layer explanation, category guidance, and legacy migration note make this complete for a discovery/recommendation tool with no safety concerns. The tool has no destructive or mutating behavior implied, and all 4 parameters are mapped to use cases.

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 100%, so the schema already documents all 4 parameters well. The description adds the mapping of level→parameter usage (level 1 uses task_description, level 2 uses category, level 3 uses skill_id), which adds meaning beyond raw schema. However, this mapping is implicit rather than explicitly stated as a level-to-parameter correlation table, so it adds moderate but not rich value beyond the 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?

The description clearly states this tool finds ecosystem skills/plugins with a specific verb+resource. It breaks down the three-layer progressive loading system (quick recommend, category browse, full detail), giving strong specificity. It also distinguishes itself from the many ecosystem_* sibling tools by focusing on discoverability/recommendation rather than repo management or scanning.

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 explains what each of the 3 levels is for (describe task, browse by category, get full detail) and which inputs map to which level. It doesn't explicitly say when NOT to use this vs. alternatives, but it does clarify that the integration category absorbed what used to be the ecosystem_recipes tool, which helps the agent route correctly. It provides clear context for choosing the right level, though it doesn't enumerate alternative tools to prefer.

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