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

Annotations declare non-destructive, closed-world, non-read-only; the description adds real behavioral context beyond them — that generation consumes the workspace's inference credit and that the call may return `needs_confirmation` (matching the approvalId param). This is valuable disclosure, though the return format is not fully elaborated.

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?

Three sentences, front-loaded with the core purpose and the axis mechanism, then cost and confirmation notes. Efficient with no obvious filler, though the opening all-caps framing is slightly rhetorical.

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 7-param generative tool with no output schema, the description covers purpose, cost implication, and the confirmation flow, which are the key things an agent needs. It stops short of detailing return content, but that is largely minor here.

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 86%, so the schema already documents params (including count default, direction default, and workspace scoping rules). The description adds little param-level meaning beyond restating 'named semantic axis' and 'four directions', so baseline 3 applies.

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), resource (a Prism node), and mechanism (named semantic axis, four directions) with concrete axis examples. An agent can clearly distinguish this generation gesture 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?

Positions the tool as 'THE core Prism gesture' and gives axis examples, implying when to reach for it, but never states when NOT to use it or contrasts with alternatives such as prism_nodes_research. Usage is implied rather than delineated.

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