SkillsPicker

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, but the description goes beyond them: it promises 'no code leaves the machine' (a privacy guarantee), previews the return shape (match count against 3,000+ skills, 2 picks with source, license and install command), and discloses the paid upsell ($9 one-time for the full ranked list). That pricing and privacy disclosure is information the agent cannot get anywhere else and is directly relevant to how it should frame results to the user.

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?

Front-loaded with the core action and trigger conditions, and there is no filler. The middle trigger sentence is a long run-on list, and the final sentence mixes return-shape preview with marketing copy, which costs a little crispness, but every clause carries information an agent can act on.

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?

No output schema exists, so the description carries the burden of describing returns — and it does, specifying the match count, two picks with source/license/install command, and the link structure. Combined with the privacy guarantee and trigger conditions, an agent has everything needed to decide when to call it and how to relay results.

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 the baseline is 3, but the description adds genuine meaning: it establishes a preference order among the three optional parameters (derive tags from local files such as package.json/pyproject.toml/go.mod/Cargo.toml so nothing leaves the machine; repo_url and description are fallbacks). It doesn't add format or validation detail beyond the schema, so it stops short of 5.

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 and resource — 'Recommend free, open-license agent skills (SKILL.md) for the current project' — with the qualifier 'free, open-license' that scopes what kind of skills. There are no sibling tools to differentiate from, and the purpose is unambiguous on first read.

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?

Explicit triggers are enumerated: starting a new project, setting up a repo, asking which skills/plugins to add for Claude Code, Cursor, Codex, Copilot or Gemini CLI, mentioning SKILL.md or Cursor rules, or asking how to improve the agent on a given stack. It also gives a preference order for inputs (derive tags from local files first, then description, then repo URL), which is actionable routing guidance rather than vague context.

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