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

Annotations already indicate it's mutating and destructive, and idempotent. The description adds behavioral context: 'Returns unreviewed trust; never grants a Verified badge,' and specifies authentication requirements, complementing the annotations without contradiction.

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?

Two sentences front-loading purpose and requirements with no superfluous text. Every word adds value.

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?

With 10 parameters (0% schema coverage), no explanation of 'files', 'truncated', or output schema (though it exists). The description omits workflow integration with siblings like resource_detail or search_resources, leaving agents underinformed for a complex publishing action.

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 0%, so the description must compensate, but it only mentions 'semantic version' and 'idempotency key' out of 10 parameters. It fails to explain critical parameters like 'files', 'name', 'tags', etc., leaving agents without necessary context.

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 states the verb 'publish' and the resource 'agent resource package' (canonical hosted package release). It distinguishes from siblings like publish_markdown_to_harness by specifying 'immutable canonical hosted package release' and 'never grants a Verified badge.'

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 prerequisites: 'confirmed-user Bearer with active superskill:managed scope, semantic version and idempotency key.' It clearly indicates the tool is for publishing packages, but lacks explicit exclusions or alternatives.

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