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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description is not carrying the safety burden alone. It adds real context beyond them: the created object is always a draft and publishing happens in the dashboard, and an MCP key with edit permission is required — both are behaviors an agent can't infer from the annotations.

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, front-loaded with the core action, then the draft-only boundary and auth requirement. No filler; the parenthetical about list_templates is dense but directly useful for calling the 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 mutation tool with no output schema and a nested doc object, the description covers the key risks: it never publishes, requires an edit-capable key, and where template_key comes from. Minor gap: no indication of what is returned on success (e.g., a paywall/draft identifier) or how the nested doc is validated.

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 provenance the schema lacks: template_key must come from list_templates and specifically the webview templates, and doc is the alternative to a template rather than a complement. It leaves the mutual exclusivity of template_key and doc implied rather than stated.

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 ('Creates a draft paywall') and distinguishes the two creation sources: a Studio template key or a supplied document. It also routes to the sibling list_templates for keys, which helps separate it from read/update tools, though it never explicitly contrasts itself with save_paywall_doc or validate_paywall_doc.

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?

'It is never made live: going live is done in the dashboard' clearly sets the scope boundary and tells the agent not to look for a publish path here. 'from list_templates — the webview ones' gives concrete guidance for obtaining template_key, but no explicit when-not or comparison against the update/validate siblings.

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