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

Adds substantial behavior beyond annotations: a second AI from another model family reviews the change, credits are estimated first, charged only on completion and never on failure, and it returns a studio link plus a project id. The annotations only cover the safety profile (non-read-only, non-idempotent), so this billing/review/return disclosure is genuinely additive.

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 the action and the mode split, then behavior, then billing, then return value. No filler and nothing repeated from the schema.

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 three-parameter creation tool with no output schema, the description covers the mode choice, the asynchronous review/build process, the cost model, and the return payload. Everything an agent needs to decide and call correctly is present.

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%, so the baseline is 3, but the description adds consequence-level meaning the schema lacks: what 'website' vs 'app' actually produces and where a website can be published. It does not add formatting hints for name/description beyond the schema text.

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 and resource ('Start building a new app or website on SPOE from a description') and immediately splits the resource into its two concrete variants, website vs app, each with its stack. An agent can tell this apart from app_status/list_apps/check_handle without opening any schema.

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 clear selection criteria between the two modes ('website' = fast plain HTML, publishable at name.spoe.dev; 'app' = full-stack Next.js/Fastify/Postgres) and points to app_status for tracking the build. It does not state any when-not conditions or what to do for an existing project, so it stops short of the top band.

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