image_registry_data

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

Annotations include readOnlyHint=true and destructiveHint=false, and the description aligns by emphasizing 'without pulling it' and being a read operation. It adds crucial behavioral context: it uses the daemon's cached credentials, making it dependent on daemon state, and highlights a security risk of logging auth_config. This exceeds annotation coverage.

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 moderately concise, with the core purpose stated early. It includes a security note and parameter docs, which are useful but slightly verbose. The structure is clean, but the security section could be tightened, though it's not excessive.

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 registry meta-data tool with no output schema, the description covers the purpose, mechanism, and security. It explains return values as a dict with Descriptor and Platforms. However, it doesn't mention edge cases like when the daemon is not running or credentials fail, nor does it clarify the exact structure of nested objects. Still, it's fairly complete for its 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?

Schema description coverage is 0% (no descriptions in the schema), so the description must compensate. For `repository`, it says 'Image reference' but adds little beyond the name. For `auth_config`, it explains it as registry credentials and provides context about usage, which is marginally helpful. However, it doesn't clarify the expected format or handling of nested objects, leaving it somewhat vague.

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 function: get registry data for an image without pulling it, via the daemon's distribution endpoint. It contrasts with a sibling tool (registry_manifest) for direct registry access, and mentions resolving the remote descriptor and platform list. This effectively differentiates it from similar registry tools 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?

The description explicitly tells when to use this tool versus the alternative (registry_manifest) and when to avoid it. It says to prefer `docker login` and leave `auth_config` unset for security, and explains the mechanism (daemon's cached credentials). This is strong guidance for decision-making.

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