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

With no annotations, the description carries the full burden and does so: it discloses the sandbox execution model (scripts run but cannot reach emdly, cookies, or owner data), a 2 MB size cap, public link visibility ('anyone with the link can open it'), and the data-safety implication (never put customer data or secrets in it). It also states that earlier versions remain viewable.

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?

Front-loaded with what gets produced and the returned link, then constraints. The parenthetical enumerations of design types and page layouts are long but informative; nearly every clause carries a distinct constraint (sandbox, size, visibility, versioning).

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 annotations and no output schema, the description supplies what an agent needs: the return value (a URL of a known shape), versioning behavior, sandbox isolation, size limit, and confidentiality warning. Nothing material is left unspecified.

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 per-parameter documentation already exists and the baseline is 3. The description adds real meaning beyond that by explaining the semantics of `design` (hash or URL; new version, stable link, prior versions preserved) rather than restating the schema.

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 (publish) and resource (design), enumerates what a design can be (banner set, page layout, e-mail, component, feature), and names the returned artifact (https://emdly.com/designs/<hash>). This clearly separates it from sibling read tools design_get and design_list.

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 describes the two modes: omit `design` to publish new, pass `design` to publish a new version of an existing one, including the consequence that the link stays stable. It also gives a policy constraint ('publish only what the owner asked for or agreed to — otherwise offer it first'). It does not name sibling alternatives, but the create-vs-update routing is unambiguous.

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