image_inspect

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

The readOnlyHint and destructiveHint annotations already signal safe read-only behavior, and the description adds meaningful behavioral context: it is local-only, does not pull, includes specific fields like config and layer digests, and is equivalent to docker inspect. A small gap is that it doesn't mention error behavior for malformed or absent image IDs, but it covers the most important operational constraints.

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 front-loaded with the core purpose and output contents, then quickly pivots to when to use alternatives, then states the local-only constraint and the parameter/returns reference. Each sentence adds necessary information, and the Arg/Returns formatting keeps it scannable without unnecessary filler.

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?

Given the tool has one string parameter, no output schema, and annotations already covering read-only safety, the description conveys enough to call and use the tool correctly. It explains the scope, output shape, key distinctions from sibling tools, and the parameter semantics, so all needed contextual information for successful invocation is present.

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?

The schema only defines `id_or_name` as a string with no description, but the description's Args section explains it as 'Image name (with optional tag/digest) or id.' This is exactly the semantic value the schema lacks. It might benefit from one concrete example, but for a single straightforward parameter it is sufficiently actionable.

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 opens with a precise statement: 'Return the full inspect detail for a single local image.' It clarifies the object scope (local image), the operation (inspect), and the expected output shape (config, size, layer digests, RepoTags/RepoDigests). This clearly distinguishes it from siblings like image_list, image_history, and image_registry_data.

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 provides explicit usage guidance and alternatives: use image_list for quick overviews of many images, image_history for per-layer build history, and image_registry_data/registry_manifest for remote manifests without pulling. It also states the tool's limitation upfront with 'Only inspects images already present locally,' giving an agent clear routing conditions.

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