Get a list of all image builds (composes) with their UUIDs and basic status.

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

Annotations include readOnlyHint=true, so the description does not need to reiterate that. The description adds context beyond annotations: it explains the return structure (UUID, name, status, created_at) and provides an example response. It also mentions a link to the UI. No contradiction with annotations.

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, front-loaded with the key instruction, and uses bullet points and an example response. Every sentence adds value, and it is concise without being terse.

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's simplicity (list with pagination and search), the description covers purpose, usage, parameters, return structure, and an example. It does not mention error conditions or empty responses, but these are minor omissions. The output schema is implied by the example response.

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 coverage is 100% with descriptions for all three parameters. The description adds value by reiterating default values (limit 7, offset 0) and providing usage guidance for offset (asking user if they want more composes). It also explains the search_string as substring search.

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 explicitly states 'Get a list of all image builds (composes) with their UUIDs and basic status.' It uses a specific verb+resource and distinguishes from sibling tools like get_compose_details by stating that this returns the UUID needed for that tool.

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 strong usage guidance: 'ALWAYS USE THIS FIRST' when checking image build status or finding builds. It lists common use cases and instructs to ask the user about adapting offset for pagination. It does not explicitly state when not to use, but the context makes it clear.

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