Save a skill

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

Annotations already indicate a mutating, non-idempotent write, and the description adds that the skill merges into the workspace Skills library and appears alongside built-ins in list_skills. It does not disclose important behavior such as whether saving a skill with an existing name overwrites it or creates a duplicate, which matters given idempotentHint is false.

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 dense yet efficient: it defines the resource with examples, states the required directive form, and mentions the resulting library placement. Every sentence earns its place with no filler or redundancy.

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 creation tool with no output schema, the description provides enough context for an agent to decide what to pass and why. The only notable gap is the unspecified behavior on name collisions, but overall the tool is adequately specified.

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 meaningful semantics beyond the schema: the directive must be distilled, imperative, self-contained, and applied to future ads, and it provides name-style examples. This elevates the parameter guidance above mere schema repetition.

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?

Clearly states the action (Save) and resource (reusable custom SKILL), and defines what counts as a skill with concrete examples like hook formula, UGC recipe, and specialist persona. It also anchors the tool in the Skills library via list_skills, but it does not explicitly contrast with the sibling save_playbook, which uses overlapping 'playbook' language.

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 implies when to use the tool: to save a reusable creative directive applied to future ads, and it gives guidance on directive quality (imperative, self-contained). However, it never explicitly states when not to use it or how it differs from alternative save_* tools such as save_playbook.

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