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

Annotations only flag destructive/not-idempotent/openWorld; the description adds the operational specifics an agent needs: same-URL reuse, a hard 20-preview cap, published-link validation that rejects editor and builder-share URLs, and that update replaces the selected link. It also discloses boundaries outside the tool's reach (credentials stay human-only on the portal, pairing happens on the phone, iPhone only opens own previews). This is unusually rich behavioral context beyond the structured hints.

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?

Nearly every clause carries operational weight — caps, link validation, human-only boundaries — with little filler. The style is telegraphic and jumps straight into 'Creation requires intent:new' without an orienting first sentence, and fragments like 'At cap: Delete an existing preview to add another.' cost some readability.

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 destructive, multi-mode tool with no output schema, it covers intent routing, quota limits, validation rules, and human-only steps well. Minor omissions remain: the name parameter's role in creation and what a 'preview' maps to on the portal are left implicit, assuming domain familiarity.

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; the description earns extra credit by explaining how parameters combine per intent (app_link + preview_id for legacy updates, preview_id required for update and omitted for new) and by warning 'never infer updating an existing preview when they ask for a new one'. The optional name parameter is never mentioned in the description, leaving one small gap.

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 names three concrete operations (list, new, update) on previews and describes what each does, e.g. 'list returns account preview names, published URLs, IDs and creation times' and 'update requires the customer-selected preview_id and replaces that link'. It lacks a single front-loaded purpose sentence, so the agent must assemble the tool's identity from scattered clauses. Still far clearer than the title alone, and it distinguishes the modes that the intent enum selects.

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 explicitly routes intent: 'Creation requires intent:new', update needs app_link + preview_id, and list is a distinct mode. It also states exclusions and fallbacks: editor/builder-share links are rejected, at the 20-preview cap you must delete an existing preview first, and password/credential handling plus phone pairing are human-only on the portal. That is when/when-not/alternative coverage in compact form.

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