haops_create_skill

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

With no annotations provided, the description carries full transparency burden. It discloses that insertion sets version=1 and isCurrent=true, that it is admin-only and feature-gated, and that it returns the new skill row or 409 on conflict. This is good, but lacks details on whether the operation is idempotent (it is not, as 409 indicates), and doesn't specify if the returned 'skill row' contains all fields. Still, it provides essential behavioral context for safe invocation.

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 four sentences, each serving a distinct purpose: main action, versioning detail, access/feature gate, and return/conflict behavior. It is front-loaded with the core purpose and avoids unnecessary elaboration. No word is wasted.

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 8 parameters (6 required), enums, no output schema, and no annotations, the description covers the key points: scope handling, versioning, conflict resolution, access controls, and return type. It could mention the exact structure of the returned row or whether the skill is immediately active, but it provides sufficient completeness for an agent to decide and invoke correctly.

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% with each parameter described. The description adds value beyond schema by clarifying the 'scope'-'projectSlug' dependency (scope=system omits projectSlug, scope=project requires it), the versioning semantics (version=1, isCurrent=true), and the conflict behavior. This extra context helps the AI understand parameter relationships beyond individual descriptions.

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?

Description starts with 'Create a new agent skill (system or project-scoped)', which clearly states the verb and resource. It also explicitly distinguishes from sibling tools like haops_update_skill by noting conflict resolution, and from haops_bulk_publish_skills by implying this is for single skill creation. The purpose is unmistakable and unique among siblings.

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 explicitly states 'Admin-only on the server, gated by ENABLE_COMPOSED_PROTOCOLS', indicating prerequisite context. It also provides explicit when-not guidance: '409 if a skill with the same name already exists... use haops_update_skill to publish a new version instead'. This gives clear direction on when to use this tool vs an alternative.

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