Lookup Image

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

Annotations already cover readOnly, openWorld and non-destructive, so the lower bar applies; the description still adds real context by disclosing the authentication model (no token needed) and the supported-registry restriction that bounds the open-world lookup. It also explains the failure shape ('image is null when the image is not found'), which annotations cannot convey. It omits whether lookups are rate-limited or cached.

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?

Three short sentences ordered by importance: what it does, access constraints, then accepted registries. No filler, no restatement of the title, and the null-return note is placed last where it belongs.

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?

With no output schema, the description does the right minimum work by describing both returned artifacts and the not-found sentinel. Annotations cover the safety profile. The remaining gap is the `ref` syntax, which an agent must guess before making its first call.

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 0% for the single `ref` parameter, so the description must carry the meaning, and it only partially does: the registry allow-list implies that `ref` may include a host like ghcr.io or quay.io, which helps. The required format (registry path, tag, digest?) is never spelled out, and the only named field, `image`, is a return value rather than a parameter, which could momentarily confuse an agent reading the one-param 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?

It states a specific verb and resource ('Look up a public Docker image') and, unusually, also declares the second artifact returned ('the one-service compose file that runs it'). The word 'public' and the read-oriented phrasing visibly separate it from generateImage and the inspect* siblings.

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?

The description sets hard scope boundaries (public images only, no token needed, an explicit allow-list of eight registries), which effectively tells the agent when this tool will succeed and when it will not. It never names an alternative sibling or states when to prefer inspectPublicSource/generateImage instead, so the comparative guidance is only implied.

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