image_push

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

Annotations only say readOnlyHint=false and destructiveHint=false, which are minimal. The description adds substantial behavioral context: it requires the image to be pre-tagged, explains how private registries need credentials, and warns that auth_config credentials may be logged verbatim by MCP clients, recommending docker login instead. It also discloses the return type as a string. These go beyond annotations and are highly informative.

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 well-structured and front-loaded. The first sentence states the purpose, followed by necessary pre-requisites and behavior, then a security note, and finally Args/Returns. Every sentence contributes value—there is no fluff or repetition. It is concise yet comprehensive.

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?

For a push tool with three parameters and a simple string output, the description covers all essential aspects: the pre-requisite tagging, behavior for bare names, credential requirements and security caveats, and the return type. It also implies edge cases (private registries) and provides a safe default (docker login). The presence of an output schema for the string return means no further return documentation is needed. This is complete for an agent to call the tool correctly.

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 input schema lists three parameters (repository, tag, auth_config) but provides no descriptions. The description compensates partially: it explains the meaning of repository and tag via the 'image_tag it with the registry-qualified repository[:tag]' phrase, and it details auth_config's role and security implications. However, it does not explicitly document the optional tag's default behavior or the exact structure of auth_config. Given 0% schema coverage, the description adds meaningful semantics but leaves some gaps.

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's purpose: 'Push an image or repository to a registry.' It uses a specific verb (push) and resource (image/repository), and distinguishes itself from siblings like image_pull or image_tag by naming the required pre-requisite (image_tag) and the behavior of bare names. An agent can immediately understand what this tool does.

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 gives explicit when-to-use guidance: it explains the pre-requisite (image_tag the image with the registry-qualified name), notes that a bare name pushes to Docker Hub, and provides alternatives for authentication (system_login or docker login). It also advises to prefer docker login for security, effectively telling the agent when to avoid auth_config. This is explicit and actionable.

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