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

Annotations already declare destructive, non-idempotent, and open-world behavior. The description adds substantial context beyond that: sandboxed opaque-origin serving, no cookies/session, CSP restrictions, upload checks for empty/oversized/off-origin content, and the allowed root-relative /lib/ imports. It leaves some gaps, such as replay/overwrite behavior for an existing app id and how ownership is verified.

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?

The description is front-loaded with the core purpose, but it is long and somewhat repetitive, restating off-origin enforcement in both the upload-check and CSP sentences. The component list and runtime guidance are relevant, yet the overall density is higher than necessary for a two-parameter publish tool.

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 publishing tool with no output schema, the description covers the runtime environment, import rules, and validation checks thoroughly. It does not explain what the tool returns, how ownership is enforced, or what happens when republishing over an existing app id, which are meaningful gaps for a destructive write operation.

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 baseline is 3, but the description adds meaning beyond the schema: it specifies that html must be a complete self-contained document derived from the model's view prompt, that root-relative /lib/ imports are allowed, and that checks reject empty, oversized, or off-origin content. This helps an agent construct the html parameter correctly.

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 states a specific verb and resource: 'Publish the generated application for a model you own' and defines the artifact as the single-file HTML produced from the model's view prompt. It does not, however, distinguish this tool from sibling publish tools like sim_publish or sim_publish_compare, so an agent cannot route between them from the description alone.

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?

Clear context is provided: the tool applies to a model you own and to HTML generated from that model's view prompt, with detailed runtime and template guidance. It stops short of explicitly comparing this tool to sibling alternatives such as sim_publish or sim_publish_compare, and it gives no exclusion conditions.

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