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

Annotations already declare readOnly/openWorld=false/destructive=false, and the description adds substantial context beyond them: non-text or >300,000 byte reads are refused, the viewer URL expires in 10 minutes, visibility is unchanged, the URL opens only that artifact, and there is a 60/key/hour rate limit returning `rate_limited`. These are exactly the operational constraints an agent needs before calling.

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-loading is excellent—the 'without artifact / with artifact' split frames the whole tool in the first two clauses—and every sentence carries unique information. It is, however, densely packed with parentheticals and backticked tokens that reward careful reading rather than skimming.

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?

There is no output schema, and the description compensates by naming the returned fields (URLs, `live`, versions, published flag, paths, `declaration`, `url`/`expiresAt`). For a zero-required-parameter read tool with four optional knobs, nothing an agent needs in order to call it correctly is missing.

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 only 25% (just `artifact`), so the description must compensate and does: it defines the semantics of `artifact` (id or slug), `path` and `version` (read that file as text, default published index.html), and `open` (returns url/expiresAt, optional version). It also supplies the default that the schema omits.

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 states a specific verb+resource and splits behavior by parameter presence: without `artifact` it lists your artifacts newest-first with URLs and `live`, with `artifact` it lists versions, published state, paths and `declaration`. That mode-splitting makes it trivially distinguishable from siblings like super_artifact_set, which it explicitly names as the mutation path.

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 gives explicit when-to-use routing: add `path` or `version` to read a file as text, use `open: true` with `artifact` for a viewer URL, and go to super_artifact_set to change what is served or who can open it. Exclusions and alternatives are both named rather than inferred.

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