registry_manifest

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

Annotations indicate readOnly and non-destructive. The description adds context about direct HTTPS communication, stripping of colon/at in repository, and optional credentials. Does not contradict annotations. Some minor gaps like potential error handling could be included.

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?

Well-structured with a concise first sentence, followed by details, alternatives, and parameter list. No redundant information. Front-loaded with the core action.

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 lack of output schema, the description provides a clear return format. It covers all necessary aspects: purpose, behavior, parameters, and alternatives. Highly complete for the tool's complexity.

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?

Despite zero schema description coverage, the description thoroughly documents each parameter with examples, defaults, and constraints. It clarifies that username/password override environment variables and that reference defaults to 'latest'.

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 purpose as fetching a repository's manifest without pulling, and distinguishes between single-platform and multi-platform manifests. It also names alternative tools (buildx_imagetools_inspect and image_registry_data) for similar tasks.

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?

Explicitly mentions when to use the tool (to inspect registry manifests) and provides alternatives for different scenarios, such as using docker CLI or daemon. Also explains the behavior regarding tags and digests.

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