image_load

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

Annotations only indicate readOnlyHint=false and destructiveHint=false, which are minimal. The description compensates by detailing behaviors: from_file is read by the server's user, ~ is expanded, in-band data is base64-encoded, and from_file streams straight to the daemon. It also specifies the return as a list of inspect payloads. This goes beyond the annotations without contradicting them.

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?

The description is appropriately structured with a purpose statement, usage guidance, and a clear Args/Returns section. It front-loads the core function and differentiates from siblings early. There is a minor redundancy in repeating 'exactly one of data/from_file' twice, but it is otherwise efficient and readable.

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?

The tool has two mutually exclusive parameters and no output schema, so the description must cover parameter choice, input handling, and return format. It explains the encoding issue, the file streaming, and the return list. It also ties back to image_save and distinguishes from related tools. Nothing essential 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 0%, so the description carries the full burden. It thoroughly documents both parameters: data is 'Tarball contents' and from_file is 'Path to a tarball produced by docker save / image_save', and emphasizes that exactly one must be provided. This adds complete meaning beyond the bare 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?

The description clearly states the tool loads an image from a tarball produced by image_save, specifying the two input modes (data or from_file). It explicitly differentiates from image_pull and image_import, and names the counterpart image_save, making the tool's role unambiguous among 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?

It provides explicit guidance on when to use alternatives: 'when the image lives in a registry, image_pull is the normal route' and 'for a flat rootfs archive that is not a docker save bundle use image_import'. It also gives a recommendation between data and from_file, explaining that from_file is preferred for anything but small images due to base64 encoding overhead.

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