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

Annotations only declare it is a non-read-only, non-destructive write. The description adds two useful traits beyond that: it consumes workspace inference credit and may return a `needs_confirmation` state. It does not, however, explain what confirmation entails or what the generated output looks like.

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 tight sentences, front-loaded with the operation and the axis concept. The 'THE core Prism gesture' framing is mild marketing but does not obscure the information.

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 generation tool with no output schema and high schema coverage, the description covers the essentials: what it produces, that it costs credit, and that confirmation may be required. A note on the return shape of the variations would close the remaining gap.

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 86%, so the baseline is 3, but the description adds meaning to the `axis` parameter by giving concrete examples ('more visceral', 'for the skeptic', 'stripped to essentials'). It slightly restates the four-way direction enum rather than adding to it.

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?

States a specific verb (generate variations) and resource (a Prism node) with the scope made explicit: 'along a named semantic axis ... in one of four directions.' This clearly separates it from siblings like prism_nodes_update and prism_nodes_research.

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?

No when-to-use guidance, no prerequisites, and no named alternatives among the many prism_* siblings. The only contextual hint is the credit-cost note, which informs the agent of expense but not selection.

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