compose_pull

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

Annotations indicate non-readonly and non-destructive. The description adds context that the tool pulls images without starting containers, which is a key behavioral trait. It does not contradict annotations and provides sufficient transparency about the tool's safe, non-destructive nature.

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: a concise first sentence for the core purpose, a brief paragraph on usage and alternatives, and a clear list of parameters. Every sentence adds value without redundancy.

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 has 6 parameters and no output schema, the description covers all parameters and the return format (dict with returncode, stdout, stderr, truncated). It also provides default values and a note on timeout, making it fully self-contained.

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?

With 0% schema description coverage, the description compensates fully by explaining all 6 parameters in detail (e.g., 'services' meaning pull only those services, 'ignore_pull_failures' continuing on failure). This adds significant meaning beyond the property names in 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 'Pre-fetch images for a compose project's services without starting them.' It uses a specific verb-resource pair and distinguishes from siblings like compose_up and image_pull, which are alternative tools for related but different 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?

The description provides explicit use cases (stage images before outage window, refresh cache, verify accessibility) and explicitly states when not to use it (use compose_up --pull always for integrated pull). It also mentions the prerequisite of daemon login via system_login.

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