get_skill

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

With no annotations, the description carries the burden. It discloses validation behavior ('Rejects unknown skill ids and any path that leaves the skill directory'), the read-only nature ('documentation retrieval, not a live ads API'), and the progressive-disclosure contract for references. It doesn't cover errors for nonexistent reference files, auth, or rate limits, but for a simple retrieval tool these are not critical omissions.

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 three sentences with zero filler. The core purpose is front-loaded in the first sentence, usage guidance follows in the second, and the final sentence provides validation and identity context. Every sentence 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?

For a simple two-parameter read-only tool with no output schema and no annotations, the description covers the key context: what is returned, when to use it, the progressive-disclosure reference convention, and validation rules. It does not specify the exact response structure or behavior when an in-folder reference file is missing, but the tool is simple enough that the description is nearly 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?

Schema description coverage is 100%, so the schema already thoroughly documents both skill_id and references, including examples and path constraints. The description reinforces these semantics with 'progressive-disclosure contracts' and the rejection of path escape, but it does not add substantial new parameter-level meaning 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 opens with a specific action and resource: 'Return one skill's SKILL.md and optional named reference files.' It is clearly distinguished from list_skills (which lists skills) by saying to use it after list_skills for the full public instructions of a single skill, and from the live ads API identity statement.

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?

Explicitly says 'Use this after list_skills when you need the full public instructions for a single skill,' giving a clear when. It also instructs when to pass references (only for Markdown files in that skill folder) and that invalid ids/paths are rejected. However, it does not explicitly compare to the sibling tools get_pack_readme or get_hosted_mcp_urls, so it falls short of a full when-not/alternatives roadmap.

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