create_preview

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

No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses that deployment is automatic, that previews live on an isolated subdomain, and that live URLs are returned. It omits significant behaviors: whether authentication is required, what happens when a slug already exists (overwrite vs. conflict), whether previews persist or expire, and how the optional password gates access beyond the schema's one-line hint.

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 sentences, both reasonably short, and the core action is front-loaded. The second sentence is largely redundant with the first, repeating 'deploy' and 'live URLs' rather than contributing new information, so it does not fully earn its place.

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 only 3 fully documented parameters and no output schema, the schema bears most of the load, so the description need not explain return values. Still, for an unannotated deployment/mutation tool it is thin: no auth or permission context, no idempotency or redeploy behavior, and no note on preview lifetime.

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%, so slug, files, path, content, encoding, and password are already documented in the schema. The description adds only the notion of an 'isolated subdomain', which loosely contextualizes the slug parameter but gives no format, uniqueness, or collision semantics. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Deploy') and resource ('HTML/CSS/JS project') with a concrete outcome ('live preview URL on an isolated subdomain'). An agent can distinguish this from list_previews/get_preview_diff/delete_preview by the deployment action, though it never explicitly contrasts itself with sibling update_preview, which is the closest ambiguity.

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?

The second sentence gives a use case ('live interactive prototypes... for fast feedback'), which implies when this tool is appropriate. However, there is no explicit when-not guidance, no mention of when to use update_preview instead of re-creating, and no stated prerequisites or alternatives.

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