registry_manifest

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

Beyond annotations (readOnlyHint, destructiveHint), the description adds behavior: 'Talks HTTPS directly — no daemon or CLI needed' and explains that repository ref's :tag/@digest is stripped and passed via reference. No contradictions.

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 concise and well-structured: purpose, behavior, alternatives, parameters, and return format in a few focused sentences. Every sentence adds value.

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 annotations cover safety, the description covers purpose, behavior, parameters, alternatives, and return format (dict with specific fields). No output schema needed; description is complete.

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 0% schema description coverage, the description text thoroughly explains each parameter: repository (ref), reference (tag/digest, default latest), username and password (override env vars). This adds meaningful context beyond the 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 'Fetch a repository's manifest without pulling' and explains what it returns (single-platform or multi-platform manifest list/OCI image index). It distinguishes itself from sibling tools by naming alternatives (buildx_imagetools_inspect, 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 explicitly says when to use this tool (fetch manifest without pulling) and provides alternatives for the same question, giving clear context on when to choose this over siblings.

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