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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds material context the annotations cannot convey: the call is paid ($0.10/call via x402 USDC on Base, or 20 for $1.00 with atlas_buy_pack) and the output is a mechanical scaffold that must be rewritten, with a different return shape for voice targets. It does not cover failure modes or what happens if the character cap is exceeded.

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?

Four tight sentences, front-loaded with what the tool produces and how to treat the result; the output-disposition instruction and pricing follow logically. The pricing clause is somewhat long but carries real invocation-relevant information, so little 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?

With 9 parameters (nested objects, enums) and no output schema, the description does describe the returned artifact and its voice-target variant, which is a real contribution. However, it never explains the return envelope or the meaning of key domain terms (kit, elements mode, character cap), leaving the agent to infer a good deal.

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 100% and the nested state object is thoroughly documented, so the schema carries the parameter burden. The description adds only oblique references ('from the kit', 'the target's character cap') without clarifying how parameters like beats, control, or shows affect the output. Baseline 3 is appropriate.

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+resource: assembles a first-draft acting paragraph from the kit, fitted to the target's character cap and already linted. It references the sibling artifacts it depends on (kit, lint, targets, atlas_buy_pack), though the domain jargon ('kit', 'character cap', 'delivery line') is not defined, so differentiation from atlas_show/atlas_kit is only partial.

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?

Gives post-call guidance ('It reads mechanically: rewrite it as prose') and one output branch ('A voice target gets the delivery line instead'), plus the paid alternative atlas_buy_pack for bulk. It never states when to reach for this tool versus atlas_show or atlas_kit, so the usage guidance is implied rather than explicit.

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