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

Adds substantial behavioral context beyond the annotations: drafts persist across conversations, every version is content-screened, and flagged drafts still return a draft_id but serve a 451 preview. No contradiction with idempotentHint or destructiveHint exists.

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 compact and front-loaded with the key usage condition. Every sentence adds a distinct fact: storage location, return values, persistence, and screening behavior.

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 tool with no output schema, it names the persistent draft_id and live preview_url return values, explains the flagged-content behavior, and provides lifecycle routing to list_drafts. Combined with sibling names, an agent has the needed context to call it correctly.

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%, including the note that index.html is required for a browsable preview, so the description does not need to add much param-level detail. The description's 'for a name' aligns loosely with name_hint but adds no new semantics.

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 action (creating a draft site/page/landing) and resource (user's Scopeweb portfolio). It distinguishes from sibling update_draft through the 'nothing to edit yet' condition and from list_drafts via the 'future sessions to resume work' pointer.

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?

Explicitly states when to use: when the user wants a draft and there is nothing to edit yet. It also names list_drafts for future resumption, but could go further by explicitly saying 'use update_draft to edit an existing draft.'

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