spawn_skills

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

With no annotations, the description properly carries the transparency burden. It discloses that it reads .spawn/skills.json when present, falls back to the API without network/credentials in that case, and that refresh requires credentials. It also mentions the approximate token size for 'full' detail, giving a sense of cost. A minor gap is that it doesn't explicitly describe the response structure or error handling for API failures, but the provided context is already strong.

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 a few well-organized sentences with no filler. The core purpose and high-level usage appear first, followed by behavior and fallback guidance. Each sentence contributes new information, and the warning about skipping the tool when you already know what you need is a valuable inclusion without bloat.

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?

This is a lookup/index tool with no output schema, so the description must explain what to expect, and it does. It explains where the data comes from (local file or API), when credentials are needed, and that a wrong ID yields the list anyway. It also gives enough context about the content (skill domains, mechanic and look) to help an agent decide when to call it. The combination of purpose, usage, fallback behavior, and token-size note makes it complete for this tool's complexity.

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?

Input schema covers 100% of parameters with descriptions, so baseline is 3. The description adds meaningful value beyond the schema: it explains the detail parameter's token size implication, notes that search is case-insensitive over id/name/description, and clarifies that refresh rewrites the local index and needs credentials. projectDir also gets context about default resolution, though the schema already covers that. This lifts it above the 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 identifies the tool as a menu of skill IDs for use with spawn_skill, each with what it covers. It distinguishes itself from the sibling tool spawn_skill by framing itself as the lookup/index companion to that tool. The phrase 'Browse it when planning a build' gives a concrete verb and resource.

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 usage guidance: use it when planning a build to gather all relevant skill domains, and skip it if you already know what you need, passing IDs directly to spawn_skill. It also notes that a wrong ID will answer with this list anyway, giving a fallback behavior. This clearly differentiates when to use this tool versus the sibling spawn_skill.

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