Pull an image

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

Annotations already declare openWorldHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is largely covered. The description adds genuinely new context beyond annotations: the network/disk footprint and the requirement to confirm with the user before acting.

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 tight sentences: the action and default registry come first, the risk/confirmation note second, and the example is inline. No filler and nothing that repeats the schema or annotations.

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 an output schema present, return values need not be explained. For a single-parameter pull, the description covers action, registry defaulting, example naming, and the user-confirmation obligation, leaving no material gap.

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 100% and the schema already specifies tag format and registry-qualified names. The description still adds interpretive value by stating the default registry when none is given, which resolves an ambiguity the schema leaves open.

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 ('Download an image from its registry') plus a concrete example ('postgres:17') and the default behavior (Docker Hub unless another registry is named). The pull action is clearly separable from siblings like list_images, inspect_image, build_image and tag_image without opening the schema.

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?

Gives a real precondition: 'Uses the network and disk: confirm with the person first,' which tells the agent when extra caution is warranted. It does not, however, name alternatives or note that run_container may implicitly pull, so the when-to-use-vs-sibling routing is only partially covered.

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